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

    Neuronpedia

    INDEX
    Explanations

    classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winger
    -0.07
     đen
    -0.07
     ztr
    -0.07
    ุต
    -0.06
     inch
    -0.06
     Gus
    -0.06
     Corporate
    -0.06
    輪
    -0.06
     Анг
    -0.06
     parity
    -0.06
    POSITIVE LOGITS
    ①
    0.07
    lang
    0.07
     indicate
    0.06
    (sec
    0.06
    equipment
    0.06
    irty
    0.06
     Extremely
    0.06
     requestData
    0.06
     ethic
    0.06
     natives
    0.06
    Act Density 0.001%

    No Known Activations