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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ี้
    0.50
    ra
    0.49
    Vorlage
    0.48
    unkte
    0.47
    dır
    0.46
     jett
    0.46
    osch
    0.46
    ット
    0.44
    टी
    0.44
    dracht
    0.44
    POSITIVE LOGITS
    できる
    0.68
    ח
    0.67
    ين
    0.64
     $:
    0.63
    é
    0.63
    ма
    0.61
    с
    0.61
    ка
    0.60
    りん
    0.60
    ز
    0.60
    Act Density 0.103%

    No Known Activations