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

    Neuronpedia

    INDEX
    Explanations

    notations related to programming functions and operations

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

    bolded text or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.49
     BrowserModule
    -0.49
     étoit
    -0.47
     surla
    -0.43
     enfans
    -0.42
     citoyens
    -0.41
     hommes
    -0.41
     peines
    -0.40
     exemplos
    -0.40
     vandens
    -0.40
    POSITIVE LOGITS
     **
    1.33
    (**
    1.23
    **
    1.17
    ,**
    1.10
     '**
    1.00
     **)
    0.97
    )**
    0.97
    **)
    0.95
    ]**
    0.91
     ***
    0.91
    Act Density 0.035%

    No Known Activations