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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    los
    -0.82
    rek
    -0.78
    mund
    -0.74
    orious
    -0.72
    vir
    -0.71
    clips
    -0.71
     lame
    -0.69
    redo
    -0.68
     advoc
    -0.68
    chairs
    -0.68
    POSITIVE LOGITS
    ISO
    0.69
     Surveillance
    0.67
    idential
    0.64
     Shooter
    0.64
     Niagara
    0.63
    iously
    0.62
     Depth
    0.62
    ibility
    0.61
    icity
    0.61
     NTS
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.