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

    Neuronpedia

    INDEX
    Explanations

    terms related to constraints and limitations in various contexts

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

    preceding reasons, causes, or problems

    np_acts-logits-general · gemini-2.0-flash

    identifying risks and constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affinch
    -0.47
     depends
    -0.44
    ときは
    -0.44
     depending
    -0.43
     väli
    -0.42
     Hinblick
    -0.42
    ということは
    -0.41
     untuk
    -0.41
     keer
    -0.41
     Compostela
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.98
     때문
    0.88
    ThroughAttribute
    0.82
    UserScript
    0.80
    ValueStyle
    0.76
    transQ
    0.76
    UnusedPrivate
    0.74
     estekak
    0.73
     otomatig
    0.71
     autorytatywna
    0.70
    Act Density 0.644%

    No Known Activations