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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     toxin
    0.42
     ROY
    0.41
     شدن
    0.39
     invisibility
    0.38
    <unused432>
    0.38
     pron
    0.38
     pohyb
    0.38
    鹼
    0.38
    無法
    0.38
     FAN
    0.37
    POSITIVE LOGITS
    ataire
    0.43
    nord
    0.43
    Nord
    0.42
    archy
    0.40
    professional
    0.40
     prakty
    0.39
    olique
    0.38
    responseTime
    0.38
     Papp
    0.38
    Professional
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.