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

    Neuronpedia

    INDEX
    Explanations

    subcultures

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the word “dark,” especially when used to describe tone or humor.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .leave
    -0.07
    .InputStream
    -0.06
     Doming
    -0.06
     Shank
    -0.06
     Apprentice
    -0.06
     comparative
    -0.06
    λεκ
    -0.06
     interpreted
    -0.06
    IRROR
    -0.06
     arrives
    -0.06
    POSITIVE LOGITS
    GuidId
    0.07
     hesitation
    0.07
     DWORD
    0.07
    าผ
    0.06
     ز
    0.06
     Но
    0.06
     nabí
    0.06
    세
    0.06
     lø
    0.06
     Tony
    0.06
    Act Density 0.032%

    No Known Activations