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

    Neuronpedia

    INDEX
    Explanations

    <?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hut
    -0.07
     fug
    -0.07
     forecasts
    -0.07
     Produto
    -0.07
    “All
    -0.06
     по
    -0.06
    "All
    -0.06
     regist
    -0.06
     llama
    -0.06
     dispos
    -0.06
    POSITIVE LOGITS
    剛
    0.07
     완
    0.07
     Inline
    0.06
     Ấn
    0.06
    yne
    0.06
    _MSB
    0.06
    <?,
    0.06
     Grades
    0.06
    erdings
    0.06
     गलत
    0.06
    Act Density 0.001%

    No Known Activations