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

    Neuronpedia

    INDEX
    Explanations

    care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bundan
    -0.06
     návště
    -0.06
     مردم
    -0.06
    <?>>
    -0.06
    然而
    -0.06
     Initializes
    -0.06
     Về
    -0.06
    ulist
    -0.06
     Williamson
    -0.06
     ناح
    -0.06
    POSITIVE LOGITS
     mos
    0.07
     gider
    0.07
    velop
    0.07
     vy
    0.07
    detector
    0.07
    AL
    0.07
    mkdir
    0.07
    isateur
    0.07
     kendisi
    0.07
    "struct
    0.07
    Act Density 0.005%

    No Known Activations