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

    Neuronpedia

    INDEX
    Explanations

    programming code fragments

    np_max-act · gemini-2.0-flash

    The neuron is triggered by file path segments and file names (including their extensions) in directory or file‐listing tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Worlds
    -0.07
     Кон
    -0.07
     Architect
    -0.06
    _GEN
    -0.06
     emission
    -0.06
    album
    -0.06
     Canyon
    -0.06
    EINVAL
    -0.06
    ,label
    -0.06
     Μαρ
    -0.06
    POSITIVE LOGITS
    лены
    0.07
    .Reverse
    0.07
    ับท
    0.07
    stered
    0.07
     khẳng
    0.07
     pojist
    0.07
    、それ
    0.07
    ction
    0.06
     أع
    0.06
     项
    0.06
    Act Density 0.186%

    No Known Activations