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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    PLA
    -0.75
    ndra
    -0.75
     blaster
    -0.73
     Economist
    -0.73
    ocratic
    -0.69
    atorial
    -0.68
    è»
    -0.67
    ãĤª
    -0.65
    NING
    -0.65
     Reload
    -0.63
    POSITIVE LOGITS
    \":
    0.69
    Vers
    0.69
    edge
    0.69
    wine
    0.69
    Birth
    0.67
    Normal
    0.66
    cember
    0.66
    holes
    0.63
     upgr
    0.62
    ornings
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.