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

    Neuronpedia

    INDEX
    Explanations

    pone

    np_max-act · gemini-2.0-flash

    This neuron identifies inline citation markers—that is, journal abbreviations (e.g. “pone”) and their accompanying numeric reference identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Multiline
    -0.06
     tents
    -0.06
     Promotion
    -0.06
    //
    -0.06
    .next
    -0.06
     jiný
    -0.06
    くれた
    -0.06
    constants
    -0.06
     Pilot
    -0.06
     feu
    -0.06
    POSITIVE LOGITS
    .setMessage
    0.07
    affe
    0.06
     getClass
    0.06
     боль
    0.06
     cried
    0.06
    (view
    0.06
     cuatro
    0.06
     docking
    0.06
    ."),↵
    0.06
     αγ
    0.06
    Act Density 0.001%

    No Known Activations