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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash

    This neuron detects the word “Still” used as a transitional marker at the start of sentences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HDMI
    -0.07
     Chrom
    -0.07
     Auditor
    -0.07
    439
    -0.07
     elem
    -0.06
    sum
    -0.06
     Pav
    -0.06
    -compatible
    -0.06
    WOOD
    -0.06
     Πανεπ
    -0.06
    POSITIVE LOGITS
     Still
    0.12
    still
    0.10
     still
    0.09
    Still
    0.09
     rest
    0.07
    してる
    0.07
    -submit
    0.07
    _St
    0.07
    _hresult
    0.07
    呆
    0.06
    Act Density 0.006%

    No Known Activations