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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on tokens representing floating-point numeric values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    CASE
    -0.07
    昌
    -0.06
    OutOfRange
    -0.06
    feof
    -0.06
     CO
    -0.06
     IE
    -0.06
    ITU
    -0.06
    님
    -0.06
    een
    -0.06
     CASE
    -0.06
    POSITIVE LOGITS
     Sey
    0.07
     echoes
    0.07
     JFactory
    0.07
     Played
    0.06
    (dot
    0.06
     Gardens
    0.06
     kích
    0.06
                        
↵
    0.06
     طب
    0.06
    .ai
    0.06
    Act Density 0.027%

    No Known Activations