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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sign
    0.48
     ત
    0.47
    lo
    0.46
    tipo
    0.46
    ウザ
    0.44
    వ
    0.44
    service
    0.44
     бекер
    0.44
    ي
    0.44
    Shin
    0.44
    POSITIVE LOGITS
     Cardiology
    0.57
    ایی
    0.55
     पोहो
    0.52
    ppelin
    0.51
    amburger
    0.51
     Salzburg
    0.50
     Bamberg
    0.50
     Midlands
    0.50
    μού
    0.49
     juggling
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.