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

    Neuronpedia

    INDEX
    Explanations

    generation, means,Parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зо
    0.54
    ですか
    0.44
    於
    0.43
    为
    0.42
    фо
    0.42
    ரோ
    0.42
    ząd
    0.42
     посмотреть
    0.41
    3
    0.40
    дом
    0.40
    POSITIVE LOGITS
    憊
    0.51
     unsteady
    0.48
     ț
    0.46
     ratings
    0.46
     nä
    0.46
    arger
    0.45
    celi
    0.45
     ']
    0.45
     thigh
    0.44
     తీవ్ర
    0.44
    Act Density 0.005%

    No Known Activations