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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lagrangian
    0.83
     Draw
    0.80
     hayan
    0.80
     Hit
    0.77
     Grun
    0.74
     Кроме
    0.73
    値
    0.72
     Soda
    0.71
     Show
    0.71
     Bound
    0.70
    POSITIVE LOGITS
    gill
    0.88
    Kate
    0.83
    income
    0.83
    beam
    0.82
    obedience
    0.82
    0.82
    economy
    0.82
    rind
    0.80
    physics
    0.80
    catering
    0.79
    Act Density 0.000%

    No Known Activations