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

    Neuronpedia

    INDEX
    Explanations

    health risk studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ерк
    -0.08
    lığın
    -0.07
    ZR
    -0.06
     cư
    -0.06
    きな
    -0.06
    _salary
    -0.06
    _conditions
    -0.06
     الو
    -0.06
    손
    -0.06
    files
    -0.06
    POSITIVE LOGITS
     Newsp
    0.07
    .PREFERRED
    0.07
    BarButtonItem
    0.07
     employ
    0.06
     Serve
    0.06
    尽
    0.06
    ,S
    0.06
     confirm
    0.06
     affirmed
    0.06
     '';
↵
    0.06
    Act Density 0.068%

    No Known Activations