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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of placeholder entity tokens of the form “NAME_‹number›” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ительное
    -0.07
    otechnology
    -0.07
    $
    -0.07
    trainer
    -0.06
    ibu
    -0.06
     паль
    -0.06
     mafia
    -0.06
    áže
    -0.06
    isi
    -0.06
     commits
    -0.06
    POSITIVE LOGITS
     arbe
    0.07
     учеб
    0.06
     نب
    0.06
     [].
    0.06
    indrical
    0.06
     Sov
    0.06
    ernals
    0.06
     předch
    0.06
    �
    0.05
     �
    0.05
    Act Density 0.030%

    No Known Activations