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

    Neuronpedia

    INDEX
    Explanations

    parentheses and semicolon

    np_max-act · gemini-2.0-flash

    This neuron is essentially “dead” and does not respond to any tokens—it never activates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uating
    -0.06
    ені
    -0.06
     TREE
    -0.06
    _UNKNOWN
    -0.06
    rar
    -0.06
     purchase
    -0.06
    _PTR
    -0.06
     Thursday
    -0.06
     lis
    -0.06
    官
    -0.06
    POSITIVE LOGITS
    ']");↵
    0.07
    "/>↵
    0.07
     федераль
    0.07
    よりも
    0.06
    くらい
    0.06
     Sub
    0.06
    ]}"↵
    0.06
    SplitOptions
    0.06
    oola
    0.06
     ""↵↵
    0.06
    Act Density 0.114%

    No Known Activations