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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document class declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.49
    .”
    0.48
    .
    0.48
     使っ
    0.46
    .»
    0.45
    .\"
    0.44
    itty
    0.44
    sl
    0.43
    ación
    0.42
    でき
    0.41
    POSITIVE LOGITS
    棻
    0.46
    ষণ
    0.46
    蒺
    0.46
    Resistance
    0.45
     Matemat
    0.45
     أساس
    0.44
     السنوات
    0.44
     Byzant
    0.43
     高校
    0.43
    Alternatives
    0.43
    Act Density 0.001%

    No Known Activations