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

    Neuronpedia

    INDEX
    Explanations

    various programming and data manipulation functions

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

    Mathematical or symbolic notation

    np_acts-logits-general · gemini-2.0-flash

    replacing/substitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.59
    PageContext
    -0.53
    GridColumn
    -0.53
    tema
    -0.51
    noscript
    -0.50
     çı
    -0.49
    Palmarès
    -0.47
     Dim
    -0.46
     Themes
    -0.45
    uarts
    -0.45
    POSITIVE LOGITS
     replacing
    1.17
     replace
    1.17
     replacement
    1.14
     remplacement
    1.11
    Replacing
    1.10
     replaces
    1.08
     Replacing
    1.06
    replace
    1.06
     remplace
    1.01
     substitution
    0.99
    Act Density 0.543%

    No Known Activations