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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical structures and variables

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

    variables associated with weights in a computational or mathematical context

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

    mathematical notation or code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Twelve
    -0.58
     Tenth
    -0.58
     twelfth
    -0.55
     Thirteenth
    -0.55
    Twelve
    -0.55
     twelve
    -0.54
     Thirteen
    -0.53
    Thirteen
    -0.52
     tenth
    -0.52
     Fourteenth
    -0.52
    POSITIVE LOGITS
     doInBackground
    0.77
    SharedDtor
    0.72
    INSEE
    0.67
     Audiodateien
    0.66
     архивлан
    0.64
     NUKAT
    0.64
    cshtml
    0.64
    Obrázky
    0.64
    estacks
    0.63
     dAtA
    0.63
    Act Density 0.051%

    No Known Activations