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

    Neuronpedia

    INDEX
    Explanations

    Title slide or image description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    序号
    0.84
    lonitrile
    0.83
    概述
    0.83
    অর্থাৎ
    0.83
     ϕ
    0.79
    ("<
    0.79
    anness
    0.79
    [*
    0.77
    Seqlist
    0.77
    उस
    0.77
    POSITIVE LOGITS
    www
    1.17
    WWW
    1.09
     www
    1.08
     Photo
    0.95
    inside
    0.95
    PHOTO
    0.94
     WWW
    0.91
    ❱
    0.89
     inside
    0.88
     photo
    0.88
    Act Density 0.022%

    No Known Activations