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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    罚
    -0.07
    ulse
    -0.06
     appe
    -0.06
     يم
    -0.06
    SKIP
    -0.06
    (ExpectedConditions
    -0.06
     undead
    -0.06
    泊
    -0.06
     odpověd
    -0.06
     právní
    -0.06
    POSITIVE LOGITS
    experimental
    0.07
    	page
    0.07
    )',
    0.07
    .US
    0.07
    exercise
    0.07
    _page
    0.07
    trag
    0.07
    ISED
    0.07
     использования
    0.06
     +:+
    0.06
    Act Density 0.000%

    No Known Activations