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

    Neuronpedia

    INDEX
    Explanations

    Approved for, plasma donation, rewards program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     だけ
    0.85
    akannya
    0.83
     tidak
    0.79
    🥵
    0.78
     változat
    0.77
     другими
    0.74
     másik
    0.74
     impossibile
    0.74
    เท่านั้น
    0.73
     tetapi
    0.73
    POSITIVE LOGITS
     tzv
    0.67
     your
    0.63
    /
    0.63
    Util
    0.62
    0
    0.59
    2
    0.59
    C
    0.59
     tzw
    0.59
    R
    0.58
    U
    0.58
    Act Density 0.009%

    No Known Activations