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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    liner
    -0.74
     Pupp
    -0.73
    /-
    -0.67
    buck
    -0.67
    liners
    -0.65
     Blaze
    -0.64
     Marshal
    -0.62
    ns
    -0.61
     Raw
    -0.60
     Lu
    -0.60
    POSITIVE LOGITS
    MpServer
    0.78
    phabet
    0.72
    ormal
    0.71
    ivable
    0.71
    hement
    0.71
    icer
    0.70
    GoldMagikarp
    0.70
    oliath
    0.69
    »Ĵ
    0.69
    emort
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.