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

    Neuronpedia

    INDEX
    Explanations

    fields of study

    np_max-act · gemini-2.0-flash

    The neuron responds to Italian-language words and phrases, effectively detecting when the text is in Italian.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pnl
    -0.08
    \Factory
    -0.07
     Psychiat
    -0.07
    locs
    -0.07
     arter
    -0.07
    طة
    -0.06
     зб
    -0.06
    퇴
    -0.06
     Jungle
    -0.06
    achten
    -0.06
    POSITIVE LOGITS
     Discovery
    0.06
     Bare
    0.06
     Above
    0.06
     j
    0.06
    _support
    0.06
    Evento
    0.06
     rev
    0.06
    archs
    0.05
     Derived
    0.05
    _objects
    0.05
    Act Density 0.038%

    No Known Activations