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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     والم
    0.87
     and
    0.85
     ומ
    0.83
     নির
    0.80
     وم
    0.75
    Automatically
    0.73
    MW
    0.72
    <0xCE>
    0.71
    ὢ
    0.71
    何か
    0.70
    POSITIVE LOGITS
    saint
    0.95
    ilizar
    0.92
    u
    0.89
     полага
    0.86
    ཋ
    0.85
    sterling
    0.84
    amak
    0.83
     Sink
    0.83
    text
    0.82
    oram
    0.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.