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

    Neuronpedia

    INDEX
    Explanations

    providing answers or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.63
     a
    0.59
    It
    0.51
    -
    0.49
    <
    0.48
    I
    0.47
     sulfur
    0.46
     cinema
    0.45
    0.44
    A
    0.44
    POSITIVE LOGITS
    ות
    0.55
     這個
    0.54
     フィ
    0.52
    на
    0.52
     Mannschaften
    0.51
     チ
    0.49
     Paryayvachi
    0.49
     Algunos
    0.48
     ディ
    0.47
    値を
    0.47
    Act Density 0.438%

    No Known Activations