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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ANCE
    -0.88
    JUST
    -0.87
    IFE
    -0.73
    issance
    -0.73
    ufact
    -0.72
    Kn
    -0.71
    YN
    -0.71
    minster
    -0.69
    Import
    -0.69
    Writ
    -0.69
    POSITIVE LOGITS
    atic
    0.71
    agraph
    0.69
    rats
    0.68
    entric
    0.68
     sympathetic
    0.67
    etting
    0.67
    agonist
    0.67
    gap
    0.66
    atan
    0.65
    agically
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.