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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    utra
    0.86
    wartz
    0.81
    worthy
    0.79
    worth
    0.78
    urium
    0.75
    ionale
    0.74
    किला
    0.74
    ergic
    0.74
    worthiness
    0.74
    ikala
    0.73
    POSITIVE LOGITS
     ubiquitous
    0.81
    fh
    0.80
     sidewalks
    0.79
    为一个
    0.79
     طل
    0.77
    fim
    0.77
     campsites
    0.77
     drunk
    0.76
     sensible
    0.76
     விழுப்புரம்
    0.75
    Act Density 0.000%

    No Known Activations