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

    Neuronpedia

    INDEX
    Explanations

    scientific data

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens and measurement values (e.g. flow rates, numeric data).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    енном
    -0.07
     Ces
    -0.07
    Annotation
    -0.07
    �
    -0.07
    aits
    -0.06
    _courses
    -0.06
    rowable
    -0.06
    итет
    -0.06
    اکی
    -0.06
    icação
    -0.06
    POSITIVE LOGITS
    _gui
    0.06
    (edit
    0.06
    .д
    0.06
    ,''
    0.06
    	make
    0.06
    WND
    0.06
     ethn
    0.06
    _leg
    0.06
    μιουργ
    0.06
     Ard
    0.06
    Act Density 0.045%

    No Known Activations