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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash

    This neuron responds to the pipe‐delimited markup of tables (the “|” column separators and header/separator lines) in documentation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erialize
    -0.07
     pursuit
    -0.07
    	assert
    -0.06
    尋
    -0.06
     disturbances
    -0.06
    ิตย
    -0.06
     resistance
    -0.06
     ngắn
    -0.06
     drain
    -0.06
    Linear
    -0.06
    POSITIVE LOGITS
     disagree
    0.07
     PYTHON
    0.07
    =forms
    0.06
     VARIABLE
    0.06
     кра
    0.06
    QUENCY
    0.06
     gonna
    0.06
    шее
    0.06
     IPA
    0.06
    Erro
    0.06
    Act Density 0.009%

    No Known Activations