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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     geomet
    -0.06
     rocked
    -0.06
    mock
    -0.06
    妮
    -0.06
    _ext
    -0.06
    -controlled
    -0.06
     picture
    -0.06
     Temple
    -0.06
     Luft
    -0.06
    면적
    -0.06
    POSITIVE LOGITS
    .vis
    0.06
     aktif
    0.06
     haf
    0.06
     aslında
    0.06
     sta
    0.06
     dospěl
    0.06
     gw
    0.06
    ậ
    0.06
    	be
    0.06
     Installation
    0.06
    Act Density 0.011%

    No Known Activations