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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens that introduce examples or enumerate categories (e.g. “e.g.,” “types,” “number of,” “for example”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ьер
    -0.06
     ::=
    -0.06
    št
    -0.06
    -service
    -0.06
    audit
    -0.06
     accompagn
    -0.06
    [float
    -0.06
    Thing
    -0.06
    (ec
    -0.06
     ontvangst
    -0.06
    POSITIVE LOGITS
     TextBox
    0.07
     weren
    0.07
     tekrar
    0.06
    全面
    0.06
     Tomáš
    0.06
    rootScope
    0.06
    .panelControl
    0.06
    Rare
    0.06
    不能
    0.06
    .title
    0.06
    Act Density 0.040%

    No Known Activations