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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мех
    -0.08
     Fifth
    -0.06
     sampling
    -0.06
     valeurs
    -0.06
     critics
    -0.06
     coinc
    -0.06
     Gonz
    -0.06
     проблеми
    -0.06
    (surface
    -0.06
     Verg
    -0.06
    POSITIVE LOGITS
     APPLE
    0.06
    mp
    0.06
    ,options
    0.06
    eed
    0.06
     liste
    0.06
    Iterator
    0.06
    cant
    0.06
     implode
    0.06
     volver
    0.06
     мої
    0.05
    Act Density 0.045%

    No Known Activations