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

    Neuronpedia

    INDEX
    Explanations

    ep

    np_max-act · gemini-2.0-flash

    The neuron detects specific chemical substance names or technical chemical terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Puzzle
    -0.07
    TA
    -0.07
     Range
    -0.06
     range
    -0.06
     THEY
    -0.06
    TestFixture
    -0.06
     executives
    -0.06
    /find
    -0.06
    .Helper
    -0.06
    Label
    -0.06
    POSITIVE LOGITS
     أنه
    0.07
    stopped
    0.07
    체
    0.07
    0.07
    hood
    0.07
     kolej
    0.07
     hå
    0.06
     بوده
    0.06
     \''
    0.06
    0.06
    Act Density 0.052%

    No Known Activations