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

    Neuronpedia

    INDEX
    Explanations

    colon/equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slapped
    -0.08
    公开
    -0.07
     carrying
    -0.07
    晃
    -0.07
    豐富
    -0.07
    割
    -0.07
    ㈲
    -0.06
    一下子就
    -0.06
    쵸
    -0.06
    axe
    -0.06
    POSITIVE LOGITS
     Appalach
    0.07
     Fashion
    0.07
     FOOT
    0.07
    Regression
    0.07
    _SEC
    0.07
    hood
    0.07
    .layouts
    0.07
    健康产业
    0.07
    武侠
    0.07
    .dynamic
    0.07
    Act Density 0.062%

    No Known Activations