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

    Neuronpedia

    INDEX
    Explanations

    elements related to versioning and file metadata

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

    Code, directory, and version information

    np_acts-logits-general · gemini-2.0-flash

    code or configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })*/
    -0.73
    .[/
    -0.71
    ();*/
    -0.61
    __()
    -0.61
    });*/
    -0.60
    *}$
    -0.60
    )}</
    -0.60
     &___
    -0.60
    ExtendWith
    -0.59
    []){
    -0.58
    POSITIVE LOGITS
    1.45
    ;

    0.80
    

    0.75
    .

    0.74
     

    0.65
    ,

    0.63
     للمعارف
    0.62
    >

    0.62
    :

    0.61
    *

    0.59
    Act Density 0.180%
    No Known Activations