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

    Neuronpedia

    INDEX
    Explanations

    polar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    polar
    -1.56
     polar
    -1.46
     Polar
    -1.30
    Polar
    -1.30
     polarization
    -1.16
     polarized
    -1.16
     polarity
    -1.06
     Polarization
    -1.02
    polarized
    -0.98
     polaire
    -0.70
    POSITIVE LOGITS
    ized
    0.87
    ization
    0.78
    izable
    0.75
    tagext
    0.74
    izing
    0.73
     Majefty
    0.71
     Efq
    0.71
    ised
    0.69
    AnchorStyles
    0.69
    RectangleBorder
    0.68
    Act Density 0.307%

    No Known Activations