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

    Neuronpedia

    INDEX
    Explanations

    background/secondary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ise
    -0.07
     racist
    -0.07
    Loader
    -0.06
     behavior
    -0.06
    交流
    -0.06
    .isnan
    -0.06
    /include
    -0.06
     involve
    -0.06
    .openapi
    -0.06
    差异
    -0.06
    POSITIVE LOGITS
     לפעמים
    0.08
     progressed
    0.07
    _animation
    0.07
    ')}}"
    0.07
    _TR
    0.07
    _EP
    0.07
    ']}}</
    0.07
    .ReadAsStringAsync
    0.07
    ceptar
    0.07
    暴风
    0.06
    Act Density 0.030%

    No Known Activations