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

    Neuronpedia

    INDEX
    Explanations

    Lack of resources/limitations

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric expressions (digits, percentages, measurements) and statistical data in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ко
    -0.07
     pride
    -0.07
    鬼
    -0.06
    Disc
    -0.06
    Player
    -0.06
    school
    -0.06
    加
    -0.06
     школи
    -0.06
    анні
    -0.06
    Receipt
    -0.06
    POSITIVE LOGITS
     vrch
    0.06
    (Global
    0.06
    >/
    0.06
    λα
    0.06
    .deepcopy
    0.06
     Elijah
    0.06
    ;width
    0.06
    ataires
    0.05
     �
    0.05
     đu
    0.05
    Act Density 0.040%

    No Known Activations