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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etry
    -0.82
    visor
    -0.70
    lest
    -0.68
    itas
    -0.63
    elo
    -0.63
    omsky
    -0.59
     Languages
    -0.57
    itation
    -0.57
     dosage
    -0.56
     Appropri
    -0.56
    POSITIVE LOGITS
    Ô
    0.84
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.79
    ãĤ´ãĥ³
    0.76
     Franch
    0.75
    æ©
    0.71
    nen
    0.69
     FW
    0.68
    akeru
    0.68
    images
    0.68
    ãĥ´ãĤ¡
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.