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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron is tuned to detect decimal numeric values (floating-point measurements) typically reporting quantitative assay or analysis results.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .x
    -0.07
     Away
    -0.06
    ,DB
    -0.06
     organs
    -0.06
    .MiddleRight
    -0.06
    阿
    -0.06
    ,U
    -0.06
    .T
    -0.06
     Smy
    -0.06
    _CLEAN
    -0.06
    POSITIVE LOGITS
    ataire
    0.06
    改革
    0.06
    example
    0.06
    ][]
    0.06
     stej
    0.06
     nghiên
    0.06
     taşıy
    0.06
     produits
    0.06
    riad
    0.06
    ossa
    0.06
    Act Density 0.034%

    No Known Activations