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

    Neuronpedia

    INDEX
    Explanations

    curves and bends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Welfare
    0.39
     Brigade
    0.38
     Ping
    0.37
    нная
    0.36
    撃
    0.36
     welfare
    0.35
    anzia
    0.35
    यची
    0.35
    fisher
    0.35
    ઠવા
    0.35
    POSITIVE LOGITS
     curves
    2.08
     bends
    2.03
     curvas
    1.90
     curve
    1.88
     bend
    1.86
     Curves
    1.78
    curves
    1.71
     curva
    1.68
    Curves
    1.67
    曲线
    1.61
    Act Density 0.017%

    No Known Activations