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

    Neuronpedia

    INDEX
    Explanations

    Hil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fist
    -0.07
     Blast
    -0.07
     stones
    -0.07
     Pets
    -0.07
    />
    -0.07
    طف
    -0.06
    공
    -0.06
     terre
    -0.06
    簕
    -0.06
     fragments
    -0.06
    POSITIVE LOGITS
    增长
    0.07
    底
    0.07
    здрав
    0.07
    台账
    0.07
     развит
    0.07
    素质
    0.07
    profiles
    0.07
    ◗
    0.07
    ANTED
    0.07
     upside
    0.07
    Act Density 0.004%

    No Known Activations