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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    /
    0.93
    ,
    0.82
    ative
    0.81
    ,/
    0.75
     identity
    0.69
    ,-
    0.68
     exposé
    0.67
     investigations
    0.67
     honored
    0.67
    ys
    0.66
    POSITIVE LOGITS
    With
    0.86
     With
    0.82
     Because
    0.81
    😋
    0.80
     Roughly
    0.80
     stromal
    0.79
    One
    0.78
     çünkü
    0.78
     bakter
    0.77
     branca
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.