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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is triggered by HTTP/2 implementation identifiers—especially include/import paths and frame‐type names tied to the HTTP/2 transport layer.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Parent
    -0.07
    .guild
    -0.06
     Centers
    -0.06
    currentUser
    -0.06
     کر
    -0.06
     порядок
    -0.06
    Animations
    -0.06
    onation
    -0.06
     bindActionCreators
    -0.06
     шту
    -0.06
    POSITIVE LOGITS
     deprived
    0.07
     examine
    0.07
     --↵
    0.07
    105
    0.06
     sake
    0.06
     ，
    0.06
    //{↵
    0.06
    ，没有
    0.06
     digging
    0.06
     textual
    0.06
    Act Density 0.022%

    No Known Activations