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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     manhã
    1.05
    Hindu
    1.05
     bosque
    0.97
     Ді
    0.97
     quién
    0.97
    Alchemy
    0.95
     Информация
    0.95
    Doctor
    0.93
     Día
    0.92
    stituto
    0.91
    POSITIVE LOGITS
    ق
    1.06
    ان
    0.84
    varepsilon
    0.76
    情人
    0.76
    ام
    0.73
     anthrac
    0.71
    踞
    0.71
    on
    0.71
    ifolds
    0.71
    на
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.