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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (strict
    -0.07
    .awt
    -0.07
     Anal
    -0.07
    .students
    -0.07
     agency
    -0.07
     lifestyles
    -0.07
    clo
    -0.07
    .Single
    -0.07
    大城市
    -0.06
    ⎓
    -0.06
    POSITIVE LOGITS
    basename
    0.07
    seud
    0.07
    胡子
    0.07
    ละเอ
    0.07
    .DecimalField
    0.07
    AGES
    0.07
     happ
    0.07
    mult
    0.07
    Coords
    0.07
     défini
    0.07
    Act Density 0.000%

    No Known Activations