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

    Neuronpedia

    INDEX
    Explanations

    early life stages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    墙
    -0.07
    TURN
    -0.06
     تحص
    -0.06
    Coder
    -0.06
    ¸
    -0.06
    �
    -0.06
    .ec
    -0.06
     ull
    -0.06
    沃
    -0.06
     optimizing
    -0.06
    POSITIVE LOGITS
    ращи
    0.07
    .Handled
    0.07
     piel
    0.07
    _stream
    0.07
     happens
    0.07
    INFRINGEMENT
    0.06
     interior
    0.06
     monks
    0.06
     promin
    0.06
     immature
    0.06
    Act Density 0.049%

    No Known Activations