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

    Neuronpedia

    INDEX
    Explanations

    alpha, beta, ratios, radioactivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обо
    0.38
    ئن
    0.36
     ৫ম
    0.36
    ándo
    0.36
    стина
    0.36
    èg
    0.36
    面积
    0.35
    وفة
    0.35
    वती
    0.34
    ֛
    0.34
    POSITIVE LOGITS
     beta
    0.73
     Beta
    0.71
    Beta
    0.70
     alpha
    0.66
    Alpha
    0.62
     Alpha
    0.61
    alpha
    0.59
    beta
    0.58
     베타
    0.55
     theta
    0.55
    Act Density 0.010%

    No Known Activations