Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to assessments and evaluations of regulatory or policy implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    examining or considering options

    np_acts-logits-general · gemini-2.0-flash

    exploring possibilities and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.68
     knowing
    -0.61
    knowing
    -0.57
     gesuchten
    -0.57
     näin
    -0.56
    AnimationsModule
    -0.56
     Knowing
    -0.54
    alek
    -0.54
     expecting
    -0.54
    Knowing
    -0.53
    POSITIVE LOGITS
     ways
    1.56
     possibilities
    1.56
     options
    1.47
     alternatives
    1.43
     possible
    1.31
     possibility
    1.21
     Möglichkeiten
    1.20
     Possibilities
    1.18
     mogelijkheden
    1.18
    possible
    1.17
    Act Density 0.389%

    No Known Activations