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

    Neuronpedia

    INDEX
    Explanations

    values between 0 and 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    俱乐
    0.54
     책임
    0.53
    权力
    0.53
    ἢ
    0.52
    ेलकम
    0.52
    sbom
    0.51
    职务
    0.50
    acariy
    0.49
    缝
    0.49
    责任
    0.49
    POSITIVE LOGITS
     amplitude
    0.91
     grayscale
    0.89
     scaling
    0.88
     amplitudes
    0.82
     values
    0.82
     gradient
    0.82
     brightness
    0.80
     Gaussian
    0.79
     normalized
    0.77
     range
    0.77
    Act Density 0.360%

    No Known Activations