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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     utterances
    1.24
     môn
    1.06
     cosines
    1.06
     trouva
    1.03
     piggy
    1.02
    quito
    1.01
     території
    1.00
    ßt
    1.00
    вят
    0.99
     dovet
    0.99
    POSITIVE LOGITS
    s
    1.24
    d
    1.21
    nd
    1.08
    な
    1.07
    cerr
    1.06
    ně
    1.04
    𝘴
    1.03
    র
    1.03
    r
    1.00
    ために
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.