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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cocinar
    0.53
     добав
    0.43
     actúa
    0.43
     estilos
    0.43
     agreg
    0.42
    ुक
    0.42
     upheaval
    0.41
     acompañado
    0.41
     psyche
    0.40
     lensing
    0.40
    POSITIVE LOGITS
    ->
    0.44
    以上に
    0.44
    leder
    0.44
     fromi
    0.42
    在新
    0.42
    ledger
    0.41
    astus
    0.41
     이상의
    0.41
    Mutable
    0.40
     middle
    0.40
    Act Density 0.011%

    No Known Activations