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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron reliably activates on decimal numbers or numeric values (i.e. measurements or percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     catches
    -0.07
     methodology
    -0.07
    อร
    -0.06
    ось
    -0.06
    να
    -0.06
    נ
    -0.06
    Thomas
    -0.06
     search
    -0.06
    ULA
    -0.06
     MMC
    -0.06
    POSITIVE LOGITS
    _Ex
    0.07
     Entities
    0.07
     ao
    0.06
     constit
    0.06
     kültür
    0.06
     میشود
    0.06
     Phil
    0.06
    	actor
    0.06
    readcrumbs
    0.06
    //------------------------------------------------------------------------------↵↵
    0.06
    Act Density 0.033%

    No Known Activations