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

    Neuronpedia

    INDEX
    Explanations

    elements related to structured data or lists

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

    intermediate stages or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.62
    yntaxException
    -0.60
    LLocation
    -0.60
    Tembelea
    -0.56
     SwitchCompat
    -0.55
    NewUrlParser
    -0.55
     AppCompat
    -0.54
     Palla
    -0.52
    UnusedPrivate
    -0.51
    basicConfig
    -0.50
    POSITIVE LOGITS
     Comprometido
    0.32
    larımız
    0.30
     său
    0.30
     tedesco
    0.29
     interim
    0.29
    haikusbot
    0.28
     jezelf
    0.28
    cionar
    0.28
     parvenir
    0.28
     participado
    0.27
    Act Density 0.111%

    No Known Activations