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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     soins
    0.81
    Shirts
    0.80
    Accueil
    0.79
    Establish
    0.79
    Adult
    0.78
    kiyor
    0.77
    tDBOutput
    0.76
     эсеп
    0.74
     valeur
    0.73
     العافيه
    0.73
    POSITIVE LOGITS
    to
    0.95
    ன்
    0.83
    l
    0.75
    een
    0.75
     butyl
    0.75
    tr
    0.74
    or
    0.73
    सिया
    0.73
    ory
    0.73
    me
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.