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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    鹦
    0.81
    𝗨
    0.79
    低的
    0.77
    więks
    0.75
    ية
    0.73
    减轻
    0.73
     penghargaan
    0.72
    Ҳ
    0.72
    舴
    0.72
    腈
    0.71
    POSITIVE LOGITS
    z
    0.99
    et
    0.93
    in
    0.92
     kernels
    0.86
    en
    0.84
     reals
    0.78
    at
    0.76
    n
    0.75
     axons
    0.75
     travelers
    0.74
    Act Density 0.000%

    No Known Activations