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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    на
    0.64
     to
    0.57
    ي
    0.54
     fuel
    0.50
     bilo
    0.50
    зва
    0.50
     push
    0.49
     trebalo
    0.49
     crescita
    0.49
     sailboat
    0.48
    POSITIVE LOGITS
    ele
    0.53
    âl
    0.52
    andan
    0.52
    cJ
    0.52
    cU
    0.48
    疮
    0.47
     मचा
    0.46
     आणखी
    0.46
    cF
    0.46
    isFullscreen
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.