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

    Neuronpedia

    INDEX
    Explanations

    Searching for files

    np_max-act · gemini-2.0-flash

    technical terminology related to programming and system paths.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is highly sensitive to numeric literal tokens (especially floating‐point constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     machine
    -0.07
     MACHINE
    -0.07
     machines
    -0.07
    ])).
    -0.06
     +:+
    -0.06
    оба
    -0.06
    _TW
    -0.06
     paramMap
    -0.06
     kwargs
    -0.06
    ちょっと
    -0.06
    POSITIVE LOGITS
    fel
    0.07
    neys
    0.07
    nbsp
    0.06
    .**************
    0.06
     Burma
    0.06
    puties
    0.06
     orgán
    0.06
     multin
    0.06
     Traffic
    0.06
    .ib
    0.06
    Act Density 0.023%

    No Known Activations