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

    Neuronpedia

    INDEX
    Explanations

    limited [aspect]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ด
    1.74
    ల
    1.65
    লিখিত
    1.62
    년에
    1.49
    一定会
    1.41
     headset
    1.38
     modalCard
    1.38
    慜
    1.36
    ст
    1.34
    ರ್‌
    1.34
    POSITIVE LOGITS
    gend
    1.67
    gens
    1.66
    та
    1.64
    lığ
    1.62
    f
    1.60
    cra
    1.54
    cann
    1.53
    lık
    1.52
    dır
    1.52
    s
    1.52
    Act Density 0.015%

    No Known Activations