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

    Neuronpedia

    INDEX
    Explanations

    pages, reviewer, augmentation, To, Caution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    0.54
     ज्ञ
    0.44
    ន
    0.43
    在
    0.43
    er
    0.43
     ט
    0.42
    لہ
    0.42
    禁止
    0.42
    //*
    0.41
     기름
    0.41
    POSITIVE LOGITS
     材質
    0.46
    یشه
    0.45
    selves
    0.44
    を採用
    0.44
    …).
    0.43
    <unused80>
    0.42
    )\|_{\
    0.42
    getImageFolder
    0.42
    kkue
    0.42
    ).
    0.41
    Act Density 0.000%

    No Known Activations