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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tras
    0.57
    لا
    0.54
     Bil
    0.54
     gespe
    0.54
    ق
    0.54
    ع
    0.54
    {
    0.51
     Tied
    0.50
    Celebr
    0.50
     मुसलमान
    0.49
    POSITIVE LOGITS
     biasing
    0.51
     monod
    0.50
    a
    0.49
     mungkin
    0.49
     phasor
    0.48
    d
    0.48
     steric
    0.48
    嗤
    0.47
    dial
    0.46
     buoyant
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.