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

    Neuronpedia

    INDEX
    Explanations

    Precision and accuracy

    np_max-act · gemini-2.0-flash

    This neuron detects highly technical physics experiment language, especially references to antihydrogen spectroscopy and precision measurement tests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _COMPANY
    -0.07
    retain
    -0.07
     CD
    -0.06
    _PRE
    -0.06
    ringe
    -0.06
    /update
    -0.06
     Burk
    -0.06
    ZA
    -0.06
    _WINDOW
    -0.06
     nhưng
    -0.06
    POSITIVE LOGITS
     ιστο
    0.06
     Natalie
    0.06
     月
    0.06
     enquiry
    0.06
     Fish
    0.06
     diversified
    0.06
     เส
    0.06
     Journey
    0.06
     callable
    0.06
     sense
    0.05
    Act Density 0.013%

    No Known Activations