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

    Neuronpedia

    INDEX
    Explanations

    algebraic geometry and varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สะ
    0.41
    ইহ
    0.40
    seva
    0.38
    境界層
    0.38
     micelles
    0.38
    xu
    0.38
     ③
    0.37
     Marginal
    0.37
     burned
    0.37
     Nonlinear
    0.37
    POSITIVE LOGITS
     over
    0.54
     над
    0.49
    over
    0.38
    qat
    0.37
     rationally
    0.36
     GL
    0.36
     ponad
    0.36
     ориенти
    0.36
    finity
    0.35
     схе
    0.35
    Act Density 0.008%

    No Known Activations