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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ticking
    -0.08
     Ferr
    -0.08
     Мин
    -0.08
     ferr
    -0.07
     ýer
    -0.07
     unh
    -0.07
     Федераль
    -0.07
     pudd
    -0.07
    тарына
    -0.07
     kra
    -0.07
    POSITIVE LOGITS
    ível
    0.09
    uele
    0.09
    ive
    0.09
    IVE
    0.08
    ives
    0.08
    ivir
    0.08
    olar
    0.08
    ivesse
    0.08
    ieni
    0.08
    ividad
    0.08
    Act Density 0.000%

    No Known Activations