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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects the definitional “is a” phrase that starts an encyclopedia-style entry (e.g. “X is a Y”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ト
    -0.07
     puntos
    -0.07
     import
    -0.06
     //----------------------------------------------------------------
    -0.06
     against
    -0.06
    .Position
    -0.06
    ANTS
    -0.06
     selecting
    -0.06
    idf
    -0.06
     Anne
    -0.06
    POSITIVE LOGITS
    �
    0.08
    μει
    0.07
    .comm
    0.07
     WX
    0.06
     مب
    0.06
    มาย
    0.06
     musí
    0.06
     исключ
    0.06
     đĩa
    0.06
    .cod
    0.06
    Act Density 0.003%

    No Known Activations