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

    Neuronpedia

    INDEX
    Explanations

    signal

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    nten
    -0.08
    rif
    -0.07
    LineEdit
    -0.07
    -desc
    -0.06
     přid
    -0.06
    reich
    -0.06
     Hopkins
    -0.06
    -Clause
    -0.06
    _lit
    -0.06
     Oven
    -0.06
    POSITIVE LOGITS
    ीख
    0.07
    (nx
    0.06
    (:,:,
    0.06
     ту
    0.06
    .SP
    0.06
    QL
    0.06
     JNICALL
    0.06
    音
    0.06
     Cable
    0.06
    insurance
    0.06
    Act Density 0.002%

    No Known Activations