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

    Neuronpedia

    INDEX
    Explanations

    S1 to Sn

    np_acts-logits-general · gemini-2.5-flash-lite

    variable usage contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.55
    ။
    0.52
    、
    0.49
    ،
    0.49
    이지만
    0.46
    ایی
    0.46
    5
    0.46
    지
    0.45
    ۔
    0.45
    𝘨
    0.45
    POSITIVE LOGITS
    на
    0.65
    <0x91>
    0.54
    et
    0.51
    ান
    0.51
     njeg
    0.51
    om
    0.49
     QnrB
    0.49
     Jamal
    0.48
     Maulana
    0.48
     velike
    0.47
    Act Density 0.143%

    No Known Activations