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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moments
    -0.07
     peasants
    -0.07
     gentle
    -0.07
    _sphere
    -0.06
    lena
    -0.06
    ERİ
    -0.06
    Valor
    -0.06
     agli
    -0.06
    mo
    -0.06
    aravel
    -0.06
    POSITIVE LOGITS
     Films
    0.06
    .start
    0.06
    /min
    0.06
     HttpMethod
    0.06
    -\
    0.06
    Notify
    0.06
     endIndex
    0.06
    =batch
    0.06
     approximation
    0.06
    .opens
    0.06
    Act Density 0.006%

    No Known Activations