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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    morph
    0.55
    son
    0.53
    der
    0.52
    gene
    0.49
    gob
    0.49
    ox
    0.49
    ny
    0.49
    axes
    0.49
     granular
    0.48
    nal
    0.48
    POSITIVE LOGITS
     Kiến
    0.53
    Ớ
    0.52
     někol
    0.51
    问
    0.51
     مە
    0.51
    ৬
    0.50
     섹
    0.50
    zące
    0.49
    禇
    0.49
    乐队
    0.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.