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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Divinity
    -0.74
     Koen
    -0.70
    ibrary
    -0.70
     guiActiveUnfocused
    -0.70
     Arch
    -0.68
    aceae
    -0.67
     Dating
    -0.66
    addons
    -0.66
    ournal
    -0.66
    xual
    -0.65
    POSITIVE LOGITS
    BIT
    0.75
    GH
    0.72
    Gs
    0.72
    ISA
    0.72
    NF
    0.71
    GS
    0.70
    KK
    0.69
    IDA
    0.69
    yr
    0.69
    ERG
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.