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

    Neuronpedia

    INDEX
    Explanations

    descriptive language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dou
    -0.06
     yüzden
    -0.06
    んだ
    -0.06
     merkez
    -0.06
    แก
    -0.06
    척
    -0.06
     burgeoning
    -0.06
     Grant
    -0.06
    άρχ
    -0.06
     analogue
    -0.06
    POSITIVE LOGITS
     phot
    0.08
    misc
    0.06
     potom
    0.06
    SSID
    0.06
     optical
    0.06
    ]["
    0.06
    って
    0.06
    .hy
    0.06
    (phone
    0.06
     amused
    0.06
    Act Density 0.034%

    No Known Activations