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

    Neuronpedia

    INDEX
    Explanations

    subject

    np_max-act · gemini-2.0-flash

    This neuron detects the clause in software license headers that introduces the terms or conditions (e.g. the “subject to the following conditions” part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    doors
    -0.07
     tangled
    -0.07
     authorities
    -0.07
    Police
    -0.07
     Mate
    -0.06
    _zeros
    -0.06
     Stan
    -0.06
     frantic
    -0.06
    Flight
    -0.06
    Often
    -0.06
    POSITIVE LOGITS
    |(↵
    0.07
    机关
    0.06
    より
    0.06
    луш
    0.06
    км
    0.06
    _(
    0.06
    [][
    0.06
    (水
    0.06
     {}↵↵
    0.06
    .region
    0.06
    Act Density 0.001%

    No Known Activations