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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    milo
    -0.68
    Ross
    -0.67
    ño
    -0.65
    fin
    -0.62
     whistle
    -0.62
    Tracker
    -0.61
    rower
    -0.60
    SOURCE
    -0.60
     minded
    -0.60
    isSpecialOrderable
    -0.59
    POSITIVE LOGITS
     anew
    0.79
    çĶŁ
    0.71
    ymes
    0.64
    ukong
    0.63
     belonging
    0.61
     extinct
    0.61
     rele
    0.61
    oids
    0.60
     localized
    0.60
     reapp
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.