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

    Neuronpedia

    INDEX
    Explanations

    validation rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uesta
    -0.07
     GD
    -0.07
    自卑
    -0.07
    .LoggerFactory
    -0.07
    getView
    -0.06
    安居
    -0.06
    早早
    -0.06
     bed
    -0.06
    ocalypse
    -0.06
    赴
    -0.06
    POSITIVE LOGITS
    paste
    0.07
    责编
    0.07
     getClient
    0.07
    directories
    0.07
    跟她
    0.07
     togg
    0.07
     imprisonment
    0.07
     gı
    0.07
    _REGEX
    0.07
     Invalid
    0.07
    Act Density 0.046%

    No Known Activations