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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]}"↵
    -0.06
    Cube
    -0.06
    Piece
    -0.06
    brown
    -0.06
    WebKit
    -0.06
     bytearray
    -0.06
     celkem
    -0.06
    ako
    -0.06
     gpointer
    -0.06
    出版社
    -0.06
    POSITIVE LOGITS
     aggravated
    0.06
     광
    0.06
     इसक
    0.06
    UCCESS
    0.06
    .@
    0.06
     sentimental
    0.06
    requency
    0.06
    AMA
    0.06
     Kıs
    0.06
    .product
    0.06
    Act Density 0.000%

    No Known Activations