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

    Neuronpedia

    INDEX
    Explanations

    conflict scenes

    np_max-act · gemini-2.0-flash

    The neuron fires on language describing imminent physical danger or threats, especially armed attackers advancing or perilous action in a scene.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ональ
    -0.07
    Chunks
    -0.06
     Sandwich
    -0.06
    _yield
    -0.06
    ItemCount
    -0.06
     підприєм
    -0.06
     konkrét
    -0.06
     searches
    -0.06
     bisa
    -0.06
    ısının
    -0.06
    POSITIVE LOGITS
    さんは
    0.06
    NECT
    0.06
     –↵
    0.06
    (driver
    0.06
    NSSet
    0.06
    .lineWidth
    0.06
     {},
    0.06
     scanf
    0.06
     morph
    0.06
     sts
    0.06
    Act Density 0.023%

    No Known Activations