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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the “+” operator in arithmetic expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    อท
    -0.07
    อ
    -0.07
     cil
    -0.07
    ارت
    -0.06
    queda
    -0.06
    Suc
    -0.06
    στημα
    -0.06
     composing
    -0.06
    .Zip
    -0.06
    efs
    -0.06
    POSITIVE LOGITS
    ,@
    0.07
    .destroyAllWindows
    0.07
    ONGODB
    0.07
    _ADD
    0.07
     Stuttgart
    0.06
    ностей
    0.06
     ILogger
    0.06
     забезпеч
    0.06
    .IGNORE
    0.06
    лер
    0.06
    Act Density 0.002%

    No Known Activations