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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the discourse word “so” (including standalone “So” as a conjunction/adverb).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bpm
    -0.07
     nine
    -0.06
     ngắn
    -0.06
     dudes
    -0.06
     setDate
    -0.06
    .demo
    -0.06
    369
    -0.06
     AssemblyTrademark
    -0.06
    (module
    -0.06
    دث
    -0.06
    POSITIVE LOGITS
     So
    0.09
     so
    0.08
    So
    0.08
    "So
    0.08
    -so
    0.07
     CONNECT
    0.07
    aisy
    0.07
     GIT
    0.07
     super
    0.06
    “So
    0.06
    Act Density 0.038%

    No Known Activations