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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giú
    -0.07
     epsilon
    -0.06
    鼩
    -0.06
     Zen
    -0.06
     Including
    -0.06
    "path
    -0.06
    沖
    -0.06
    命名
    -0.06
     Oprah
    -0.06
     máy
    -0.06
    POSITIVE LOGITS
    _LIGHT
    0.07
     revisit
    0.07
    lasses
    0.07
     intuitive
    0.07
     aggrav
    0.07
    两人
    0.07
    关注度
    0.07
     comprehend
    0.07
    舅舅
    0.07
    /id
    0.07
    Act Density 0.009%

    No Known Activations