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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash

    This neuron detects boilerplate license “notice” clauses—specifically the lines about not removing or altering the notice from any source distribution.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cave
    -0.06
     darauf
    -0.06
    /Z
    -0.06
    wiki
    -0.06
    atter
    -0.06
     trọng
    -0.06
     insanity
    -0.06
    restaurants
    -0.06
    ेज
    -0.06
    .Images
    -0.06
    POSITIVE LOGITS
    (dim
    0.07
    Adv
    0.07
     Тем
    0.06
    震
    0.06
     trump
    0.06
    textAlign
    0.06
    setq
    0.06
     вак
    0.06
     Deserialize
    0.06
    ilece
    0.06
    Act Density 0.000%

    No Known Activations