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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rive
    -0.07
     cursor
    -0.07
     BOTTOM
    -0.07
    .BUTTON
    -0.06
    (Current
    -0.06
    ิเว
    -0.06
     Translator
    -0.06
    ほ
    -0.06
    něné
    -0.06
    .getFirst
    -0.06
    POSITIVE LOGITS
    slick
    0.07
    قات
    0.07
     kw
    0.06
    akter
    0.06
    iesen
    0.06
     dob
    0.06
    ilon
    0.06
     recuper
    0.06
    해야
    0.06
     міг
    0.06
    Act Density 0.060%

    No Known Activations