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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    255
    -0.69
     digits
    -0.67
    ugu
    -0.67
    ãĥİ
    -0.67
    translation
    -0.67
    zag
    -0.63
    377
    -0.61
    beard
    -0.60
    gnu
    -0.59
    Ö¼
    -0.59
    POSITIVE LOGITS
    spect
    0.74
    ant
    0.74
    rest
    0.70
    cent
    0.67
     hitch
    0.64
     Viet
    0.64
    velength
    0.62
    ants
    0.62
     GOODMAN
    0.62
     Madagascar
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.