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

    Neuronpedia

    INDEX
    Explanations

    medical study data

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurement terms and quantitative medical metrics (e.g. lab indices, unit‐annotated values, and clinical measurement abbreviations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Guerr
    -0.07
    bject
    -0.07
     tales
    -0.06
     vscode
    -0.06
     approached
    -0.06
    Documento
    -0.06
    Fil
    -0.06
    ろう
    -0.06
    memo
    -0.06
     muc
    -0.06
    POSITIVE LOGITS
     McB
    0.07
     Gilbert
    0.06
    Snippet
    0.06
    _SECOND
    0.06
     Welch
    0.06
     tweaks
    0.06
     modify
    0.06
     Λ
    0.06
    -fields
    0.06
     einzel
    0.06
    Act Density 0.040%

    No Known Activations