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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming imports and getters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.70
     '\\;'
    -0.70
    TagMode
    -0.69
     autorytatywna
    -0.68
    principalColumn
    -0.66
     Италијани
    -0.66
     հղումներ
    -0.65
     Meksiku
    -0.64
    +#+#
    -0.62
    oredCriteria
    -0.60
    POSITIVE LOGITS
     he
    0.42
     Biro
    0.40
    1
    0.39
     har
    0.38
    import
    0.38
     import
    0.38
    2
    0.38
     work
    0.36
     lan
    0.35
    .*")]
    0.35
    Act Density 0.000%

    No Known Activations