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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     используется
    0.48
    <unused2146>
    0.48
    }&=
    0.48
    uradaki
    0.48
    8
    0.46
     appelée
    0.46
    s
    0.46
    ionale
    0.46
    不错的
    0.46
    page
    0.46
    POSITIVE LOGITS
    ᅬ
    0.45
    руу
    0.42
     vacuo
    0.42
     UNI
    0.41
    akh
    0.40
    າມ
    0.40
     disastrous
    0.40
     rearrangement
    0.40
     diagnosis
    0.39
    eth
    0.38
    Act Density 0.000%

    No Known Activations