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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Reneg
    -0.67
    NR
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     Mafia
    -0.64
    ghazi
    -0.64
     testim
    -0.63
    çĶ°
    -0.63
    adish
    -0.63
    Secret
    -0.61
     euth
    -0.61
    POSITIVE LOGITS
    leeve
    0.81
     largeDownload
    0.80
    peat
    0.79
    staking
    0.79
    icket
    0.75
    ickets
    0.73
     glim
    0.70
    ellar
    0.69
     arrang
    0.69
     pneum
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.