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

    Neuronpedia

    INDEX
    Explanations

    glow and bias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    2.90
    诊
    2.63
    ل
    2.61
    на
    2.52
    terrain
    2.50
    ि
    2.46
     terrain
    2.44
     säga
    2.43
     trình
    2.42
    原子炉
    2.41
    POSITIVE LOGITS
    ına
    3.52
    𝐭
    2.87
    le
    2.86
    dır
    2.65
     pria
    2.62
     suj
    2.61
    𝑤
    2.60
    ından
    2.55
    𝑡
    2.54
    tained
    2.49
    Act Density 0.114%

    No Known Activations