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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     disposer
    0.78
    URNING
    0.77
     hormati
    0.75
     tillbaka
    0.74
    <0x83>
    0.73
    ojen
    0.72
     wollte
    0.72
     hepatocellular
    0.71
     masculina
    0.70
    鸷
    0.70
    POSITIVE LOGITS
     Ча
    0.89
     Caball
    0.82
     Cols
    0.81
     Correspond
    0.81
     Conseils
    0.81
     Kb
    0.76
    Gamb
    0.75
    𝒾
    0.75
    Características
    0.74
    Indians
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.