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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    v
    0.79
     b
    0.72
     p
    0.70
    angled
    0.67
    h
    0.67
    uss
    0.66
    open
    0.65
    apple
    0.64
    \
    0.64
     B
    0.63
    POSITIVE LOGITS
    că
    0.95
    ان
    0.90
    ال
    0.88
    ෙන්ම
    0.87
    ين
    0.84
     compds
    0.82
    ین
    0.82
    са
    0.80
     iniciativas
    0.79
    ❛
    0.79
    Act Density 0.000%

    No Known Activations