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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash

    This neuron fires on floating‐point numeric values (decimal numbers), especially those reporting binding or dissociation constant measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     compl
    -0.06
     parsed
    -0.06
    UIL
    -0.06
     sweaty
    -0.06
    事務
    -0.06
    /release
    -0.06
    _DD
    -0.06
     comerc
    -0.06
    ije
    -0.06
     pep
    -0.06
    POSITIVE LOGITS
     Nathan
    0.07
    #####↵
    0.06
    actively
    0.06
    �
    0.06
    わり
    0.06
     하지
    0.06
     Attorney
    0.06
     dish
    0.06
     regards
    0.06
    ेष
    0.06
    Act Density 0.006%

    No Known Activations