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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    component
    -0.07
    ObjectContext
    -0.07
    ControlEvents
    -0.07
    Application
    -0.07
    Typography
    -0.07
    icens
    -0.07
    rown
    -0.07
    magnitude
    -0.07
     THINK
    -0.07
     обла
    -0.06
    POSITIVE LOGITS
     boobs
    0.07
    ですか
    0.07
     numéro
    0.06
    機
    0.06
    nummer
    0.06
    电视
    0.06
    _Run
    0.06
    עש
    0.06
    ﺉ
    0.06
     stealing
    0.06
    Act Density 0.000%

    No Known Activations