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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥķãĤ¡
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.76
     Stre
    -0.71
    Spread
    -0.69
     Hes
    -0.68
    ãĤ¢
    -0.68
    ãĤ»
    -0.66
    orsi
    -0.66
    Evil
    -0.65
    Loading
    -0.64
    POSITIVE LOGITS
    autical
    0.86
    uria
    0.79
     chop
    0.76
    istic
    0.76
    anship
    0.73
    cair
    0.73
    netic
    0.72
    nia
    0.71
    opolis
    0.70
    otomy
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.