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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and functions

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

    get boolean values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.98
     utafitiHapana
    -0.94
     noDo
    -0.92
    -0.85
    ########.
    -0.83
    Vidite
    -0.81
    Rüyada
    -0.81
    -------
    -0.80
    tagext
    -0.80
     Италијани
    -0.80
    POSITIVE LOGITS
     survey
    0.29
     surveyed
    0.26
    1
    0.26
    #
    0.26
    アン
    0.25
    2
    0.25
     boolean
    0.25
    boolean
    0.25
    8
    0.24
    ome
    0.24
    Act Density 0.043%

    No Known Activations