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

    Neuronpedia

    INDEX
    Explanations

    Letter in quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reel
    -0.07
    δη
    -0.07
     Odin
    -0.06
     Bowie
    -0.06
     slip
    -0.06
    Smoke
    -0.06
    来た
    -0.06
     Sutton
    -0.06
     --
    -0.06
    Baby
    -0.06
    POSITIVE LOGITS
    .toLocale
    0.07
    .");
↵
    0.07
    nonatomic
    0.06
    :',
    0.06
    ;",↵
    0.06
    ))));↵
    0.06
     USSR
    0.06
    маз
    0.06
    .Begin
    0.06
    ]):↵
    0.06
    Act Density 0.121%

    No Known Activations