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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Forbidden
    0.74
    Compras
    0.72
    禁止
    0.68
     жок
    0.68
    不允许
    0.68
     খাবার
    0.67
     yağ
    0.67
    Tidak
    0.66
     tangga
    0.66
    不
    0.66
    POSITIVE LOGITS
    亟
    0.88
     fundamental
    0.83
     internationally
    0.77
     insightful
    0.77
     increasingly
    0.76
     elucidate
    0.76
     vitally
    0.75
     urgently
    0.74
     paradig
    0.73
     vital
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.