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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wavelength
    0.41
    Went
    0.40
     হানাদার
    0.38
     dodge
    0.37
     Hedge
    0.37
    㓶
    0.37
    कामना
    0.37
    Weapon
    0.36
     wavelengths
    0.36
     porcentaje
    0.36
    POSITIVE LOGITS
     သ
    0.46
    ્ર
    0.45
    ução
    0.44
    ુ
    0.44
     సం
    0.44
     tương
    0.42
    ruzione
    0.42
     nuances
    0.41
    vação
    0.40
     под
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.