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

    Neuronpedia

    INDEX
    Explanations

    Determiners and prepositions

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on the Spanish noun “ubicaciones” (and its subtoken parts), i.e. the occurrence of that location-related term.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     specified
    -0.07
     bras
    -0.07
     clustered
    -0.07
    ocalypse
    -0.06
     moc
    -0.06
    AKE
    -0.06
    TY
    -0.06
    FONT
    -0.06
     世界
    -0.06
     Le
    -0.06
    POSITIVE LOGITS
    担当
    0.06
    gebn
    0.06
    .LogInformation
    0.06
     heaps
    0.06
    -.
    0.06
    ward
    0.06
     넣
    0.06
    ellar
    0.06
    .InnerText
    0.06
    _ADD
    0.06
    Act Density 0.170%

    No Known Activations