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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming or code structure

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

    4e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.63
    httphttps
    -0.57
    AutoScaleMode
    -0.54
     "..\..\..\
    -0.47
     zug
    -0.47
     noDo
    -0.46
     defaultstate
    -0.45
     "..\..\
    -0.44
     propOrder
    -0.43
    LookAnd
    -0.41
    POSITIVE LOGITS
     CURIAM
    0.63
     Paglinawan
    0.58
    ähteet
    0.44
    exitRule
    0.44
    actionMode
    0.43
    KommentareTeilen
    0.43
    énieurs
    0.42
    iffance
    0.41
    GEBURTSDATUM
    0.41
    IVEREF
    0.40
    Act Density 0.001%

    No Known Activations