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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with variables and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alunos
    0.91
    mıştı
    0.91
    vindos
    0.89
    ncia
    0.89
    larının
    0.87
     समितियों
    0.86
    établ
    0.85
    larıyla
    0.84
    larında
    0.84
    larınız
    0.83
    POSITIVE LOGITS
    $
    1.20
    .
    1.16
    2
    1.16
    '
    1.16
    。
    1.07
    6
    1.06
    3
    1.02
    _
    1.01
    _{
    1.00
    \
    0.97
    Act Density 0.551%

    No Known Activations