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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝐧
    1.07
     Darwin
    1.03
    ্নের
    1.01
    حن
    1.01
     veri
    0.99
     सटे
    0.98
    켜
    0.97
     consigui
    0.97
     Literally
    0.96
     Kors
    0.94
    POSITIVE LOGITS
    噜
    1.31
     ISM
    1.29
    డు
    1.25
    исленность
    1.19
    returnValues
    1.18
    presentable
    1.18
     reputation
    1.18
    accharides
    1.17
    責
    1.16
     octave
    1.15
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.