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

    Neuronpedia

    INDEX
    Explanations

    Software and different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wee
    -0.06
    τρα
    -0.06
    ента
    -0.06
     حزب
    -0.06
    ова
    -0.06
    то
    -0.06
    phoneNumber
    -0.06
    št
    -0.06
    gps
    -0.06
    vironments
    -0.06
    POSITIVE LOGITS
     přiv
    0.07
     ăn
    0.07
    .USER
    0.07
    (:,:,
    0.07
    (find
    0.07
     Jan
    0.07
    _manifest
    0.06
    .SetFloat
    0.06
     BUILD
    0.06
    (dev
    0.06
    Act Density 0.088%

    No Known Activations