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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lager
    0.74
     wt
    0.70
     lag
    0.66
     jargon
    0.64
     zijn
    0.60
     ±
    0.60
     shuts
    0.59
     ges
    0.59
     probs
    0.58
     survived
    0.57
    POSITIVE LOGITS
    ቬ
    0.66
    海上
    0.64
    they
    0.63
    Ꮽ
    0.62
    Vent
    0.61
     不需要
    0.61
     "`
    0.59
    Ε
    0.59
    她们
    0.58
    Our
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.