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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming materials or product‐body substances (e.g. polypropylene, titanium, glass, steel).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     flow
    -0.08
     Religious
    -0.07
    \User
    -0.07
     먼저
    -0.07
     physician
    -0.07
    appear
    -0.07
     Cargo
    -0.06
     merry
    -0.06
     listOf
    -0.06
    lh
    -0.06
    POSITIVE LOGITS
    аль
    0.07
     embody
    0.06
    oblins
    0.06
    bestos
    0.06
     konci
    0.06
    batis
    0.06
    สมบ
    0.06
     asbestos
    0.06
     знай
    0.06
    >:</
    0.06
    Act Density 0.099%

    No Known Activations