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

    Neuronpedia

    INDEX
    Explanations

    code assignment and variable initialization

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

    code variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dezelve
    -0.73
     zelve
    -0.70
     zoude
    -0.70
     queſta
    -0.68
     müſſen
    -0.68
    RenderAtEndOf
    -0.66
    webElementGuid
    -0.65
     ſei
    -0.65
    ſelben
    -0.65
     geſch
    -0.64
    POSITIVE LOGITS
     a
    0.33
     g
    0.32
     bad
    0.32
     convo
    0.31
     cats
    0.31
    าะ
    0.30
     b
    0.28
     iVar
    0.28
     weeds
    0.28
    vVar
    0.27
    Act Density 0.112%

    No Known Activations