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

    Neuronpedia

    INDEX
    Explanations

    negation and conditional expressions in code

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

    not defined or false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.77
    InSection
    -0.75
    TemporalType
    -0.73
    verwijspagina
    -0.72
    يميديا
    -0.69
     BoxFit
    -0.69
    Parcelize
    -0.66
    -------------</
    -0.66
    ValueStyle
    -0.65
    rungsseite
    -0.64
    POSITIVE LOGITS
     
    0.38
     reluctantly
    0.36
     NOT
    0.36
     foreign
    0.35
     Diamond
    0.34
     Montrose
    0.34
    meliharaan
    0.33
     not
    0.33
     Rockwell
    0.33
     HttpStatusCode
    0.33
    Act Density 0.009%

    No Known Activations