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

    Neuronpedia

    INDEX
    Explanations

    the number 3, but sometimes other numbers as well

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slavery
    -0.48
    ุก
    -0.48
    attenzione
    -0.48
     arbej
    -0.46
    aneo
    -0.46
    tagHelperRunner
    -0.46
    étit
    -0.46
     Furman
    -0.46
     open
    -0.46
    KURZBESCHREIBUNG
    -0.45
    POSITIVE LOGITS
     nakalista
    0.75
    Hochspringen
    0.63
    السكان
    0.61
    kloped
    0.61
    ruptedException
    0.60
    󠁢
    0.60
    UnknownFields
    0.59
     interesar
    0.59
    MigrationBuilder
    0.56
    pædia
    0.55
    Act Density 0.289%

    No Known Activations