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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures and discussions of government actions

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

    Follows a word indicating capability or inclination

    np_acts-logits-general · gemini-2.0-flash

    his or her disposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.89
    AutoField
    -0.74
    orianCalendar
    -0.69
    scriptcase
    -0.65
    EndContext
    -0.65
     mergeFrom
    -0.64
    anasia
    -0.63
     BoxDecoration
    -0.61
    RUnlock
    -0.58
     CHtml
    -0.57
    POSITIVE LOGITS
     ability
    1.77
     inability
    1.41
     desire
    1.34
     willingness
    1.34
     Ability
    1.26
    Ability
    1.23
    ability
    1.17
     tendency
    1.12
     Fähigkeit
    1.05
     belief
    1.04
    Act Density 0.754%

    No Known Activations