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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dirty
    0.46
     Trauma
    0.42
     psychopath
    0.42
     porad
    0.42
    dirty
    0.40
    APT
    0.40
     Jody
    0.40
     Ꭰ
    0.40
     दुर्गेश
    0.40
     (((
    0.39
    POSITIVE LOGITS
     equalize
    0.45
    样式
    0.43
    makeConstraints
    0.42
    整体
    0.40
     похађа
    0.40
     defocused
    0.40
    读取
    0.39
     smi
    0.39
    ERON
    0.39
     Waring
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.