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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and meanings

    np_max-act · gemini-2.0-flash

    The neuron detects tokens in etymological/name‐origin explanations (e.g. “derived,” “means,” root words, initials sources).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     peas
    -0.07
     pos
    -0.07
     finances
    -0.07
     refusal
    -0.07
     made
    -0.07
    agg
    -0.07
    border
    -0.07
    ag
    -0.06
    =title
    -0.06
     Wallpaper
    -0.06
    POSITIVE LOGITS
    �
    0.06
     GetLastError
    0.06
    /auto
    0.06
     Autodesk
    0.06
    .bat
    0.06
     correctamente
    0.06
     Kanunu
    0.06
    Navigation
    0.05
    ечно
    0.05
    RenderingContext
    0.05
    Act Density 0.073%

    No Known Activations