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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash

    words and phrases related to humorous or absurd bodily functions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by words describing game control schemes and input mechanics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     格
    -0.07
    amin
    -0.07
    ,param
    -0.06
    cstdio
    -0.06
     pist
    -0.06
     artworks
    -0.06
     cable
    -0.06
    ]!='
    -0.06
    �
    -0.06
    ourt
    -0.06
    POSITIVE LOGITS
    ?:
    0.07
    _REPO
    0.06
    роч
    0.06
     exclude
    0.06
    ScreenState
    0.06
     excludes
    0.06
    .squeeze
    0.06
    ucch
    0.06
    аза
    0.06
    OE
    0.06
    Act Density 0.016%

    No Known Activations