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

    Neuronpedia

    INDEX
    Explanations

    PUT

    np_max-act · gemini-2.0-flash

    information related to API implementation and best practices.

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

    This neuron does not respond to any tokens and effectively detects no patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kennedy
    -0.07
     cof
    -0.06
    .languages
    -0.06
     marine
    -0.06
    World
    -0.06
    Neo
    -0.06
    됩니다
    -0.06
     Visitors
    -0.06
     inquiry
    -0.06
     변화
    -0.06
    POSITIVE LOGITS
     toughest
    0.07
     %"
    0.07
     وب
    0.06
     threaded
    0.06
    ίο
    0.06
    eatures
    0.06
    .sp
    0.06
     Enabled
    0.06
     imageUrl
    0.06
    _dim
    0.06
    Act Density 0.004%

    No Known Activations