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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     worsens
    0.48
    لام
    0.43
    ace
    0.43
     surfactant
    0.42
     vehement
    0.41
     glycerin
    0.41
    ider
    0.40
    垐
    0.39
    adam
    0.39
     vagina
    0.38
    POSITIVE LOGITS
    রণ
    0.49
     nb
    0.46
    Williams
    0.45
     বলতে
    0.43
    рики
    0.43
     Nb
    0.42
    òria
    0.42
    Whether
    0.42
     Bereiche
    0.42
    ঝ
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.