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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ススメ
    0.38
    ͟
    0.38
    মাস
    0.37
    이사
    0.37
    ግብ
    0.36
    ობს
    0.36
    ㅅ
    0.36
    ល់
    0.36
     rehearsals
    0.36
    OLOGY
    0.35
    POSITIVE LOGITS
    coef
    0.38
    かもしれませんが
    0.37
     coef
    0.37
    кнове
    0.36
     લા
    0.36
     facteur
    0.36
     practically
    0.35
    ということです
    0.35
     末
    0.35
     Ak
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.