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

    Neuronpedia

    INDEX
    Explanations

    Proteins and/or enzymes

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “tryp” subword (e.g. in “trypsin” or “tryptophan”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     národ
    -0.06
    achsen
    -0.06
    CON
    -0.06
    네
    -0.06
     αλλά
    -0.06
     nord
    -0.06
    OUTH
    -0.06
     날짜
    -0.06
    és
    -0.06
    ails
    -0.06
    POSITIVE LOGITS
    ?('
    0.07
    Ellipse
    0.06
     supplemental
    0.06
    0.06
    itably
    0.06
    INFRINGEMENT
    0.06
     پرو
    0.06
     RecognitionException
    0.06
     suitability
    0.06
    ,'%
    0.06
    Act Density 0.002%

    No Known Activations