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

    Neuronpedia

    INDEX
    Explanations

    amino acids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    couvrez
    0.71
    ‌تر
    0.68
    ’.
    0.63
     evasion
    0.60
    0.60
     severely
    0.59
     blight
    0.59
    cup
    0.57
    ’
    0.57
     afflict
    0.57
    POSITIVE LOGITS
     pää
    0.67
     sola
    0.63
    厡
    0.63
    按摩
    0.58
    л
    0.58
    Ｓ
    0.57
    v
    0.57
     refle
    0.55
     IntegerValue
    0.55
     sexu
    0.55
    Act Density 0.001%

    No Known Activations