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

    Neuronpedia

    INDEX
    Explanations

    statements related to observation and documentation

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

    actions and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.54
    inSlope
    -0.45
     resourceCulture
    -0.44
    AndEndTag
    -0.43
     Putih
    -0.43
    Geografía
    -0.42
     Flü
    -0.40
     సౌకర్య
    -0.39
     simplifié
    -0.37
    IntoConstraints
    -0.37
    POSITIVE LOGITS
     للمعارف
    0.44
     nothwendig
    0.44
     المعرف
    0.44
    WriteBarrier
    0.41
    BufferedImage
    0.41
    CodedInputStream
    0.38
    confirmed
    0.38
     confirmar
    0.37
    uterte
    0.36
     confirm
    0.36
    Act Density 0.143%

    No Known Activations