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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    
    1.16
    el
    1.12
    邂
    1.10
    ᓵ
    1.08
    在你
    1.08
    趕
    1.06
    いです
    1.06
    员
    1.06
    不要
    1.06
    器的
    1.05
    POSITIVE LOGITS
     exertions
    1.30
    emb
    1.26
    onbury
    1.15
     cabo
    1.14
    rition
    1.14
    dice
    1.08
     Carls
    1.08
     Cren
    1.07
    mour
    1.05
    inging
    1.04
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.