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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zus
    -0.06
     fino
    -0.06
     velocity
    -0.06
     мн
    -0.06
     висок
    -0.06
     encryption
    -0.06
     romant
    -0.06
     tribunal
    -0.06
     diagon
    -0.06
     Encryption
    -0.06
    POSITIVE LOGITS
     아닌
    0.07
    ++);↵
    0.07
    (Handle
    0.07
    例
    0.07
    ělí
    0.07
    emain
    0.07
    (be
    0.06
    merchant
    0.06
     (--
    0.06
     \\
    0.06
    Act Density 0.070%

    No Known Activations