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

    Neuronpedia

    INDEX
    Explanations

    Speaking/conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ess
    -0.07
     told
    -0.07
    endez
    -0.07
    implementation
    -0.07
    遭
    -0.07
     asserted
    -0.06
    >m
    -0.06
     temas
    -0.06
     جلسه
    -0.06
     unlocking
    -0.06
    POSITIVE LOGITS
     дек
    0.06
     mennes
    0.06
     Kushner
    0.06
    .Expect
    0.06
    multip
    0.06
    $model
    0.06
    (convert
    0.06
    _COD
    0.06
    Informe
    0.06
    _timezone
    0.06
    Act Density 0.009%

    No Known Activations