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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sacred
    -0.07
     mùa
    -0.07
    علوم
    -0.07
     університ
    -0.07
    楼
    -0.07
     ETA
    -0.07
     OL
    -0.07
    (Enum
    -0.07
     ambitions
    -0.07
     nước
    -0.06
    POSITIVE LOGITS
    FFECT
    0.06
     homosexuals
    0.06
    legant
    0.06
     dbContext
    0.06
     इ
    0.06
     вы
    0.06
     FAC
    0.06
    def
    0.06
    mind
    0.06
    δέ
    0.06
    Act Density 0.011%

    No Known Activations