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

    Neuronpedia

    INDEX
    Explanations

    text that starts with the word "UPDATE" followed by a colon

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]")]
    -0.55
    Espèce
    -0.52
     veau
    -0.51
     ControllerBase
    -0.48
    logits
    -0.48
     officers
    -0.48
     Biologie
    -0.47
    prnt
    -0.47
     Svg
    -0.46
    babel
    -0.46
    POSITIVE LOGITS
     وتسجيلات
    0.75
     ddelweddau
    0.69
    SequentialGroup
    0.64
     صوتيه
    0.63
    MLLoader
    0.62
     Normdatei
    0.62
     Réponses
    0.57
     utafitiHapana
    0.56
    Portale
    0.56
    EndContext
    0.56
    Act Density 0.343%

    No Known Activations