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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    138
    -0.07
    ٥
    -0.07
    вед
    -0.07
     Pearl
    -0.07
     Tokyo
    -0.07
     Shots
    -0.06
     Major
    -0.06
    07
    -0.06
    15
    -0.06
    *T
    -0.06
    POSITIVE LOGITS
     nigeria
    0.07
     Pon
    0.06
    tero
    0.06
    .Business
    0.06
    lif
    0.06
    ":"","
    0.06
    _gray
    0.06
    GestureRecognizer
    0.06
    marketing
    0.06
    낸
    0.06
    Act Density 0.160%

    No Known Activations