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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     available
    -0.07
    $
↵
    -0.06
    (Type
    -0.06
    тивного
    -0.06
    Ped
    -0.06
     stubborn
    -0.06
     simplistic
    -0.06
    _wall
    -0.06
     Gn
    -0.06
    .Red
    -0.06
    POSITIVE LOGITS
    XHR
    0.07
     Appl
    0.07
    كييف
    0.07
     розмі
    0.06
     subtotal
    0.06
    ования
    0.06
     cade
    0.06
    삼
    0.06
     %@",
    0.06
    agle
    0.06
    Act Density 0.278%

    No Known Activations