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

    Neuronpedia

    INDEX
    Explanations

    rs followed by identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    genetic identifiers and reference numbers beginning with "rs" followed by digits.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    dataArray
    -0.77
     Eft
    -0.75
    loadData
    -0.71
    Shat
    -0.68
    mycompany
    -0.66
    Berna
    -0.65
    muy
    -0.65
     Große
    -0.64
    marg
    -0.64
    ByID
    -0.64
    POSITIVE LOGITS
     Belfast
    0.77
     remembers
    0.72
    enames
    0.72
    liston
    0.71
     Memory
    0.68
     ב
    0.68
     vase
    0.68
     Greene
    0.67
     Dos
    0.66
     Snyder
    0.66
    Act Density 0.078%

    No Known Activations