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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects the presence of legal/license header information (e.g. copyright notices, SPDX or license identifiers) at the top of source files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "↵
    -0.06
    _org
    -0.06
    conv
    -0.06
    Strike
    -0.06
    ")↵
    -0.06
    _JUMP
    -0.06
     from
    -0.06
     zat
    -0.06
    _zeros
    -0.06
    _deep
    -0.06
    POSITIVE LOGITS
    .FromResult
    0.07
     inflater
    0.07
     trava
    0.06
     Dota
    0.06
     revolutions
    0.06
    .setLayout
    0.06
    .fillRect
    0.06
     Sigma
    0.06
    yre
    0.06
     mantener
    0.06
    Act Density 0.009%

    No Known Activations