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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spoiler
    -0.06
     JsonRequest
    -0.06
     flatten
    -0.06
    はい
    -0.06
    船
    -0.06
     sans
    -0.06
     Hòa
    -0.06
    ubits
    -0.06
    ání
    -0.06
    šen
    -0.06
    POSITIVE LOGITS
    TestData
    0.08
    케이
    0.07
    ingham
    0.07
    84
    0.07
     domestically
    0.07
    .Dom
    0.06
     unemployment
    0.06
     Şubat
    0.06
    (forKey
    0.06
     Tickets
    0.06
    Act Density 0.011%

    No Known Activations