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

    Neuronpedia

    INDEX
    Explanations

    Three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Responder
    -0.07
     Emin
    -0.07
    oted
    -0.06
    事
    -0.06
    arent
    -0.06
    umpy
    -0.06
    に行
    -0.06
    ,U
    -0.06
    alat
    -0.06
    ulant
    -0.06
    POSITIVE LOGITS
     Бор
    0.07
     мал
    0.07
     primera
    0.07
    十四
    0.06
     بدان
    0.06
     discomfort
    0.06
    .all
    0.06
     Bras
    0.06
    Beginning
    0.06
     setEmail
    0.06
    Act Density 0.001%

    No Known Activations