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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     conductas
    0.90
    ಿಕ್
    0.84
    álise
    0.81
    ajt
    0.80
     paredes
    0.79
     sheath
    0.76
     retos
    0.76
     vivido
    0.76
     establecida
    0.76
    ні
    0.75
    POSITIVE LOGITS
    י
    0.88
    ي
    0.75
    y
    0.73
    ก่อน
    0.73
    急
    0.71
    ד
    0.70
    V
    0.69
    CO
    0.68
    К
    0.67
    স
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.