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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WWW
    -0.06
     Kindle
    -0.06
    ิดต
    -0.06
    ότητας
    -0.06
    _Al
    -0.06
    OF
    -0.06
    rylic
    -0.06
    ｛
    -0.06
    Bon
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     why
    0.07
     bombing
    0.07
     رنگ
    0.06
     clauses
    0.06
     Justice
    0.06
     punto
    0.06
     intelligent
    0.06
    َق
    0.06
    (register
    0.06
    pector
    0.06
    Act Density 0.003%

    No Known Activations