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

    Neuronpedia

    INDEX
    Explanations

    press

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shoe
    -0.07
    "All
    -0.07
     кв
    -0.07
     analysts
    -0.07
     beet
    -0.07
     Study
    -0.07
    (\"
    -0.06
    egrated
    -0.06
    GEN
    -0.06
     ارزی
    -0.06
    POSITIVE LOGITS
    _factory
    0.06
     responding
    0.06
     applies
    0.06
     dokument
    0.06
    饰
    0.06
    _pause
    0.06
    dialogs
    0.06
     lawful
    0.06
    _pressed
    0.06
    Configurer
    0.05
    Act Density 0.012%

    No Known Activations