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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     भारती
    1.32
    ں
    1.30
     eclectic
    1.30
     refusal
    1.28
    கடந்த
    1.27
    𝒐
    1.27
     polytopes
    1.25
     detachment
    1.25
     polytope
    1.21
     propensity
    1.19
    POSITIVE LOGITS
    či
    1.03
     noc
    1.02
     svih
    1.02
     fet
    1.01
    ز
    0.99
     gereken
    0.97
    ె
    0.95
     ông
    0.94
    ques
    0.93
    민국
    0.92
    Act Density 0.000%

    No Known Activations