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

    Neuronpedia

    INDEX
    Explanations

    website links

    np_max-act · gemini-2.0-flash

    This neuron detects pointers to additional information or references (e.g. “find more information on pages 63–79”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Arr
    -0.07
    drawing
    -0.06
     nanoparticles
    -0.06
     Dane
    -0.06
    مت
    -0.06
    ετ
    -0.06
     pont
    -0.06
    prefix
    -0.06
     visitors
    -0.06
    ث
    -0.06
    POSITIVE LOGITS
    "};↵↵
    0.08
    ){↵
    0.07
    .encode
    0.07
    ).\
    0.06
    ไซต
    0.06
     -,
    0.06
     तहत
    0.06
     จำนวน
    0.06
    =false
    0.06
    .PR
    0.06
    Act Density 0.057%

    No Known Activations