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

    Neuronpedia

    INDEX
    Explanations

    php use statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erkt
    0.45
    𒅎
    0.41
     විට
    0.41
     loadImage
    0.39
    Args
    0.38
    Loksatta
    0.38
    NewUrl
    0.37
     শর্ত
    0.37
    लीज
    0.37
     }%
    0.37
    POSITIVE LOGITS
     use
    0.40
    use
    0.40
    纳
    0.37
     Use
    0.35
    ريف
    0.34
    납
    0.33
     золото
    0.33
    hand
    0.32
     myopia
    0.32
    reliance
    0.32
    Act Density 0.000%

    No Known Activations