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

    Neuronpedia

    INDEX
    Explanations

    line slope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    круг
    0.42
    փ
    0.42
    phia
    0.39
    所の
    0.39
     मेटल
    0.39
     mechanism
    0.39
     integer
    0.38
    芻
    0.38
     ലെ
    0.38
    лая
    0.37
    POSITIVE LOGITS
     Linear
    0.63
    slope
    0.63
     Slope
    0.61
    Slope
    0.59
     slope
    0.59
    Linear
    0.55
     slopes
    0.54
     linear
    0.51
    LINEAR
    0.44
     linearity
    0.44
    Act Density 0.000%

    No Known Activations