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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ു
    0.46
    \
    0.43
     irr
    0.43
     us
    0.43
    rul
    0.42
    運輸
    0.42
    Ｌ
    0.41
    }
    0.41
    魯
    0.41
     Scattering
    0.40
    POSITIVE LOGITS
    cektir
    0.51
    objectif
    0.50
    percaya
    0.50
    രുവനന്തപു
    0.48
    errated
    0.47
     exceso
    0.47
    pesar
    0.47
     monstru
    0.46
    ugawa
    0.46
     revanche
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.