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

    Neuronpedia

    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens (e.g. counts, doses, percentages, trial phase numbers) and thus is specialized to detect quantitative data in clinical‐trial texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     jealous
    -0.07
     TMP
    -0.07
    V
    -0.06
     predator
    -0.06
    Pokemon
    -0.06
    �
    -0.06
     الص
    -0.06
     accusations
    -0.06
    nces
    -0.06
     HEADER
    -0.06
    POSITIVE LOGITS
    INFRINGEMENT
    0.07
     notorious
    0.06
    .swing
    0.06
     Ná
    0.06
                
    0.06
    JUnit
    0.06
    defined
    0.06
    ğim
    0.06
    <article
    0.06
    HBoxLayout
    0.06
    Act Density 0.018%

    No Known Activations