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

    Neuronpedia

    INDEX
    Explanations

    learning

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive and does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     jezd
    -0.07
     onions
    -0.07
     налог
    -0.07
     مرات
    -0.07
    она
    -0.06
     destac
    -0.06
     supposed
    -0.06
     Noticed
    -0.06
     таблиц
    -0.06
     realpath
    -0.06
    POSITIVE LOGITS
     lr
    0.07
     Valid
    0.07
    рин
    0.07
    (word
    0.06
    uelles
    0.06
     Event
    0.06
     сим
    0.06
    rang
    0.06
    ners
    0.06
     jTable
    0.06
    Act Density 0.003%

    No Known Activations