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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こ
    -0.07
    енное
    -0.07
     clouds
    -0.06
     Fiat
    -0.06
    τηκε
    -0.06
    Mount
    -0.06
    _l
    -0.06
     kıy
    -0.06
    _No
    -0.06
     onError
    -0.06
    POSITIVE LOGITS
     shorts
    0.07
    τέ
    0.06
    WORK
    0.06
     retrospect
    0.06
    isateur
    0.06
     brewers
    0.06
     tarn
    0.06
     работать
    0.05
     worked
    0.05
     clich
    0.05
    Act Density 0.009%

    No Known Activations