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

    Neuronpedia

    INDEX
    Explanations

    news headlines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    бот
    -0.07
    िड
    -0.06
     illumin
    -0.06
    _LOGGER
    -0.06
    ulence
    -0.06
    hei
    -0.06
     Battles
    -0.06
    _arch
    -0.06
    Writer
    -0.06
    enido
    -0.06
    POSITIVE LOGITS
     fis
    0.07
     тогда
    0.06
     dirent
    0.06
     unfavor
    0.06
     αποτε
    0.06
    latesAutoresizingMaskIntoConstraints
    0.06
    )./
    0.06
     fos
    0.06
     Ø
    0.06
     ettir
    0.06
    Act Density 0.025%

    No Known Activations