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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Loksatta
    0.87
    филлер
    0.86
     Каждый
    0.85
    ლებიც
    0.83
    屓
    0.83
     LOCCTR
    0.82
    挝
    0.82
     gradioApp
    0.81
     presenceData
    0.80
     unrivalled
    0.78
    POSITIVE LOGITS
    م
    0.83
    о
    0.81
    io
    0.73
    adores
    0.71
    а
    0.70
    وم
    0.68
     bien
    0.67
    до
    0.67
     ako
    0.66
    при
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.