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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /all
    -0.07
     jp
    -0.06
     infantry
    -0.06
     tanı
    -0.06
     péče
    -0.06
    pres
    -0.06
     chuyên
    -0.06
    (data
    -0.06
     Raises
    -0.06
     cleansing
    -0.06
    POSITIVE LOGITS
     Biz
    0.06
     cloning
    0.06
     flee
    0.06
    Clr
    0.06
     xlink
    0.06
    πον
    0.06
    Interceptor
    0.06
    CancelButton
    0.06
    lenmesi
    0.06
    [((
    0.06
    Act Density 0.026%

    No Known Activations