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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dimensions
    -0.75
    agraph
    -0.75
    ronic
    -0.68
    htaking
    -0.65
    Ħ¢
    -0.63
     dimension
    -0.62
     Dimensions
    -0.62
     Forsaken
    -0.61
     APR
    -0.61
    inav
    -0.61
    POSITIVE LOGITS
    Che
    0.74
    76561
    0.74
    ubuntu
    0.69
    uns
    0.68
    skill
    0.67
    Prev
    0.66
    inyl
    0.66
    irements
    0.65
    udo
    0.65
    $.
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.