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

    Neuronpedia

    INDEX
    Explanations

    Origins of names/titles

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of a work’s title or name—i.e. phrases explaining what something is called or where its title comes from.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    b
    -0.07
    Lv
    -0.06
    (group
    -0.06
    prices
    -0.06
     w
    -0.06
    Ingredient
    -0.06
    Tek
    -0.06
    ﾏ
    -0.06
    izers
    -0.06
    Plug
    -0.06
    POSITIVE LOGITS
    강
    0.07
     slashes
    0.07
    режд
    0.07
    南
    0.06
     Alternate
    0.06
     Geneva
    0.06
    λεύ
    0.06
     زنی
    0.06
     NSCoder
    0.06
    untos
    0.06
    Act Density 0.044%

    No Known Activations