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

    Neuronpedia

    INDEX
    Explanations

    common X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estuv
    0.95
     größere
    0.77
     kostet
    0.75
    ときは
    0.74
     herzlich
    0.73
     ･
    0.73
     político
    0.71
     Более
    0.71
     полное
    0.71
    क्षी
    0.69
    POSITIVE LOGITS
    s
    1.13
    alities
    1.05
    n
    1.00
     denominators
    0.97
     pitfalls
    0.93
     misconceptions
    0.91
     denominator
    0.89
     tropes
    0.86
     frustrations
    0.84
    ים
    0.77
    Act Density 0.014%

    No Known Activations