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

    Neuronpedia

    INDEX
    Explanations

    Software code

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric version identifiers and protocol numbers (e.g. software/framework versions or SSL/TLS version tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pey
    -0.06
     pymongo
    -0.06
     //////////////////
    -0.06
     Kardash
    -0.06
    (Block
    -0.06
    rawer
    -0.06
     //////////
    -0.06
    _IE
    -0.06
     podium
    -0.06
    =-=-=-=-
    -0.05
    POSITIVE LOGITS
     ARC
    0.07
     údaj
    0.07
    eyse
    0.07
    (group
    0.07
    GLISH
    0.07
    .swap
    0.07
    boro
    0.06
    _UTILS
    0.06
    XM
    0.06
    outfile
    0.06
    Act Density 0.226%

    No Known Activations