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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions, exponents, and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vindos
    1.35
    produtos
    1.26
     direitos
    1.21
    telefone
    1.20
     коллеги
    1.17
    pronged
    1.16
    alunos
    1.16
     денег
    1.15
    Atual
    1.13
     Apesar
    1.13
    POSITIVE LOGITS
    ap
    1.25
    ana
    1.21
    $$
    1.17
    \
    1.13
    ي
    1.12
    ening
    1.09
    g
    1.09
    .$$
    1.07
    ed
    1.06
    ay
    1.06
    Act Density 0.346%

    No Known Activations