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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Man
    -0.07
    dl
    -0.07
    /respond
    -0.06
    Unit
    -0.06
     Mick
    -0.06
    erti
    -0.06
     rounding
    -0.06
     gap
    -0.06
    ellite
    -0.06
    cie
    -0.06
    POSITIVE LOGITS
     Constructors
    0.07
     ขาย
    0.07
    ़ो
    0.06
    itis
    0.06
     comida
    0.06
    ैठक
    0.06
     flavours
    0.06
    лат
    0.06
    _tpl
    0.06
     farmers
    0.06
    Act Density 0.009%

    No Known Activations