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
    Plot
    -0.07
     ```
    -0.07
    export
    -0.07
    登记
    -0.07
    移送
    -0.06
     Nikki
    -0.06
     rescued
    -0.06
    She
    -0.06
    .s
    -0.06
    allet
    -0.06
    POSITIVE LOGITS
    _NOTICE
    0.08
    די
    0.08
     oferta
    0.07
     (++
    0.07
    遊び
    0.07
    ستراتيج
    0.07
    峰会
    0.07
    izona
    0.07
    (+
    0.07
    ત
    0.07
    Act Density 0.003%

    No Known Activations