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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gratuita
    0.75
     caffeine
    0.70
    кови
    0.68
     alimentaire
    0.68
     capitalization
    0.64
    OL
    0.64
    Fry
    0.63
     sporo
    0.63
     wildlife
    0.63
     norepinephrine
    0.62
    POSITIVE LOGITS
    ಂಥ
    0.89
    별
    0.76
    ন্থ
    0.75
     откры
    0.75
    0.75
     insiders
    0.74
    𝒔
    0.74
    。「
    0.71
    ↵↵↵↵↵↵↵↵↵↵↵
    0.71
    atable
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.