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

    Neuronpedia

    INDEX
    Explanations

    watching, looking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     /\.
    -0.07
    (!_
    -0.07
    EMAIL
    -0.06
    痄
    -0.06
    _remote
    -0.06
    キャッシング
    -0.06
    office
    -0.06
     small
    -0.06
     bustling
    -0.06
    .wh
    -0.06
    POSITIVE LOGITS
    讽
    0.08
    CAST
    0.07
     excellence
    0.07
    RARY
    0.07
     AssertionError
    0.07
    文化产业
    0.06
    صن
    0.06
     XII
    0.06
     �
    0.06
    sr
    0.06
    Act Density 0.042%

    No Known Activations