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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    П
    0.92
     Hin
    0.82
    棉
    0.79
     Cotton
    0.75
    MENTS
    0.75
    ധിക
    0.74
    Bay
    0.74
    Tv
    0.73
    作為
    0.73
     Mentor
    0.73
    POSITIVE LOGITS
     frost
    0.74
    თა
    0.74
    hausen
    0.74
     gi
    0.74
     defrost
    0.73
     frosty
    0.72
     phản
    0.71
    t
    0.70
    ei
    0.70
     glaciers
    0.70
    Act Density 0.000%

    No Known Activations