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

    Neuronpedia

    INDEX
    Explanations

    numbers with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ας
    0.83
    t
    0.82
    𝘢
    0.78
    ａ
    0.75
     согласо
    0.71
    𝐚
    0.69
    esprit
    0.68
     КА
    0.67
    ต
    0.67
     ዘዴ
    0.66
    POSITIVE LOGITS
    ق
    1.02
     in
    0.82
    ].
    0.76
    نا
    0.76
    OM
    0.75
    ]*
    0.71
    在
    0.71
    _
    0.70
    ON
    0.69
    EM
    0.68
    Act Density 0.356%

    No Known Activations