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

    Neuronpedia

    INDEX
    Explanations

    suspect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Frequency
    -0.06
     Ion
    -0.06
    Ion
    -0.06
    perience
    -0.06
     Democrat
    -0.06
    HEAD
    -0.06
     อ
    -0.06
     quotid
    -0.06
     μόνο
    -0.06
    chemical
    -0.06
    POSITIVE LOGITS
     　 　
    0.07
    Published
    0.07
    crc
    0.07
     सम
    0.06
    _timezone
    0.06
     culprit
    0.06
    (mean
    0.06
     Presents
    0.06
    ↵↵↵↵↵↵
    0.06
    íl
    0.06
    Act Density 0.015%

    No Known Activations