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

    Neuronpedia

    INDEX
    Explanations

    numbers and colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.82
    encil
    0.61
    uly
    0.59
    nton
    0.58
    clang
    0.57
    gi
    0.56
    uti
    0.55
    usi
    0.55
     शुरू
    0.55
    !
    0.55
    POSITIVE LOGITS
    an
    1.52
    is
    1.16
    ت
    1.04
    ed
    1.01
    ان
    1.00
    ن
    0.97
    ↵
    0.96
    it
    0.96
    ين
    0.96
     for
    0.94
    Act Density 0.000%

    No Known Activations