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 discourse marker phrase “the fact is” (i.e. “fact is”) used to introduce or emphasize a statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sheets
    -0.08
     downstream
    -0.07
     steam
    -0.07
    Effects
    -0.07
     classifications
    -0.07
     head
    -0.06
     مار
    -0.06
     tìm
    -0.06
     Cors
    -0.06
    (cap
    -0.06
    POSITIVE LOGITS
     статус
    0.07
     uninitialized
    0.07
     Meng
    0.06
    EntityManager
    0.06
     muži
    0.06
     найб
    0.06
    一直
    0.06
     bisexual
    0.06
    .ToolStrip
    0.06
    donnees
    0.05
    Act Density 0.011%

    No Known Activations