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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Union
    -0.64
    akeru
    -0.63
    utical
    -0.62
    à¥
    -0.61
    sports
    -0.60
    âĢ¦)
    -0.59
     Machina
    -0.59
     Cheong
    -0.57
    Untitled
    -0.57
    hip
    -0.56
    POSITIVE LOGITS
    yip
    1.02
     comr
    0.81
    Reloaded
    0.80
    ebus
    0.75
     Maul
    0.73
    gerald
    0.73
    dial
    0.71
     exha
    0.68
    Lib
    0.67
    ilib
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.