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

    Neuronpedia

    INDEX
    Explanations

    currency amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Researchers
    -0.06
    .fromString
    -0.06
    Ground
    -0.06
    EPROM
    -0.06
    .hash
    -0.06
    _AUTHOR
    -0.06
    威慑
    -0.06
     PROVIDED
    -0.06
     confined
    -0.06
    POINT
    -0.06
    POSITIVE LOGITS
    辕
    0.06
     rac
    0.06
    能力和
    0.06
    Way
    0.06
    胣
    0.06
    ৡ
    0.06
    如有侵权
    0.06
    asty
    0.06
    (lines
    0.06
    呢
    0.06
    Act Density 0.082%

    No Known Activations