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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    س
    0.73
    straße
    0.73
    ח
    0.73
    atia
    0.71
    ва
    0.71
    اس
    0.71
    су
    0.70
    स
    0.69
    ان
    0.69
    ifax
    0.68
    POSITIVE LOGITS
     polygons
    0.79
     blemishes
    0.75
    िंग
    0.72
     ugly
    0.72
     ethos
    0.72
     equally
    0.70
     mermaid
    0.70
     ’
    0.68
     scarring
    0.68
     gauging
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.