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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    0.93
    0.91
    c
    0.85
    h
    0.84
    x
    0.84
    era
    0.80
    q
    0.78
    ud
    0.78
    oc
    0.77
    b
    0.77
    POSITIVE LOGITS
     radiators
    0.80
    ائیو
    0.80
    ostics
    0.80
     infrastructures
    0.78
     nurturing
    0.76
    шат
    0.76
    也會
    0.74
    adhyay
    0.74
    ्याचा
    0.72
     inhabiting
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.