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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.87
    cknowled
    -0.81
    yssey
    -0.74
     Alchemist
    -0.73
     Jiu
    -0.69
    aturation
    -0.68
    catentry
    -0.68
     Reef
    -0.67
     Ley
    -0.65
     Bucc
    -0.64
    POSITIVE LOGITS
    urat
    0.83
    idious
    0.79
    avis
    0.67
     compat
    0.66
     Purch
    0.66
    raped
    0.66
    vest
    0.66
    licted
    0.66
    asper
    0.65
    OLD
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.