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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    *
    1.02
    e
    0.95
    スト
    0.93
    clar
    0.92
     lou
    0.91
    tec
    0.91
                
    0.90
    tdev
    0.90
    ณา
    0.89
     véritable
    0.88
    POSITIVE LOGITS
    interpolation
    1.40
     interpolation
    1.40
     metamorphosis
    1.37
     evasion
    1.35
     ascertaining
    1.35
     使っ
    1.33
    lés
    1.33
    蝣
    1.32
     absences
    1.31
     lecithin
    1.30
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.