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

    Neuronpedia

    INDEX
    Explanations

    CSS code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (from
    -0.07
     drama
    -0.07
    pretty
    -0.07
    (sort
    -0.07
     purified
    -0.06
    шись
    -0.06
     primarily
    -0.06
     Sticky
    -0.06
     chin
    -0.06
    (""));↵
    -0.06
    POSITIVE LOGITS
    enef
    0.07
     tempting
    0.06
    _rec
    0.06
     fois
    0.06
     대행
    0.06
    +r
    0.06
    zure
    0.06
     нанес
    0.06
    _PRODUCT
    0.06
     Bob
    0.06
    Act Density 0.016%

    No Known Activations