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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    상
    0.78
    も
    0.75
    ア
    0.75
    ين
    0.74
     الصحية
    0.73
    А
    0.73
    하
    0.73
    اهلا
    0.71
    香
    0.69
    𝙰
    0.69
    POSITIVE LOGITS
     gecko
    0.86
     monks
    0.84
    ковая
    0.83
     embank
    0.82
     embezz
    0.82
     daimyo
    0.80
     bhikkhave
    0.80
     receptacles
    0.80
     anodes
    0.80
     molyb
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.