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

    Neuronpedia

    INDEX
    Explanations

    more than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nouvelle
    0.47
     англий
    0.45
     İng
    0.45
     Wissenschaft
    0.44
    数学
    0.44
    承认
    0.42
     válida
    0.42
    Š
    0.41
    可能会
    0.41
     Marine
    0.40
    POSITIVE LOGITS
    arre
    0.44
    ym
    0.42
    of
    0.42
    ទេ
    0.41
    feels
    0.40
     inicial
    0.39
    stice
    0.39
    ale
    0.38
    imil
    0.38
    phase
    0.38
    Act Density 0.011%

    No Known Activations