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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ci
    -0.06
    юк
    -0.06
    _validator
    -0.06
    iểu
    -0.06
    евых
    -0.06
     мире
    -0.06
     cry
    -0.06
     بور
    -0.06
     configurations
    -0.06
    istribution
    -0.06
    POSITIVE LOGITS
    ,M
    0.08
    "user
    0.07
    MENU
    0.07
    �
    0.07
     mettre
    0.06
    _scale
    0.06
     mädchen
    0.06
     Brow
    0.06
     кус
    0.06
    _rewards
    0.06
    Act Density 0.070%

    No Known Activations