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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bans
    -0.06
     irre
    -0.06
    (block
    -0.06
    ippi
    -0.06
     nan
    -0.06
     결정
    -0.06
    .Horizontal
    -0.06
    Route
    -0.06
    processable
    -0.06
     toen
    -0.06
    POSITIVE LOGITS
     Sentinel
    0.07
    Returning
    0.06
     SUR
    0.06
     MongoClient
    0.06
     Essential
    0.06
    Adult
    0.06
     spectral
    0.06
     SOLUTION
    0.06
    인데
    0.06
    Luckily
    0.06
    Act Density 0.000%

    No Known Activations