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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fifth
    -0.08
    bred
    -0.07
    (zip
    -0.06
     constantly
    -0.06
     trở
    -0.06
    ully
    -0.06
     reef
    -0.06
    蓄
    -0.06
    /w
    -0.06
    试
    -0.06
    POSITIVE LOGITS
    nquête
    0.07
    中国队
    0.07
    wiście
    0.07
    後の
    0.07
    sław
    0.07
     Therefore
    0.07
     Casual
    0.07
    עבוד
    0.07
     AuthenticationService
    0.07
    קרו
    0.07
    Act Density 0.005%

    No Known Activations