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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ncols
    1.31
    bė
    1.27
    ണ്യ
    1.25
    нага
    1.15
    ርስዎ
    1.13
    ٹس
    1.13
    tų
    1.11
     exquis
    1.10
    astră
    1.10
    umna
    1.08
    POSITIVE LOGITS
     noon
    1.00
    훤
    0.81
     certify
    0.81
    讓
    0.79
     tud
    0.76
     summit
    0.75
     Valid
    0.75
     tional
    0.74
    환
    0.73
    whenever
    0.73
    Act Density 0.000%

    No Known Activations