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

    Neuronpedia

    INDEX
    Explanations

    code snippets including array indexing and object property access

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    styleType
    -0.82
     تضيفلها
    -0.70
     EconPapers
    -0.68
    StreetMap
    -0.66
     للاسماء
    -0.65
     oprot
    -0.65
     quæ
    -0.64
    adaptiveStyles
    -0.63
     دیکھیے
    -0.62
     CreateTagHelper
    -0.62
    POSITIVE LOGITS
    ]")]
    0.53
     vált
    0.52
    antMatchers
    0.51
    complex
    0.49
     jutaan
    0.46
     dépos
    0.46
    char
    0.46
    Complex
    0.46
    Artículo
    0.43
    isdir
    0.43
    Act Density 1.902%

    No Known Activations