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

    Neuronpedia

    INDEX
    Explanations

    code and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.66
    ↵
    0.64
    il
    0.58
    কে
    0.51
    er
    0.49
    /
    0.45
    지
    0.44
    .
    0.43
    the
    0.42
    ა
    0.42
    POSITIVE LOGITS
    _
    0.55
     کی
    0.43
    あります
    0.42
     ва
    0.41
     경우
    0.40
     fonti
    0.40
     деца
    0.40
    ၃
    0.39
    ⑶
    0.38
     كانت
    0.38
    Act Density 0.343%

    No Known Activations