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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     economic
    -0.08
     самый
    -0.07
     ein
    -0.07
     таким
    -0.07
     sebagai
    -0.07
    earning
    -0.07
    .readValue
    -0.07
    同じ
    -0.07
     Bour
    -0.07
     shm
    -0.07
    POSITIVE LOGITS
    vendor
    0.08
    𫟼
    0.07
    (cube
    0.07
    ឧ
    0.07
     copyrights
    0.07
     ocur
    0.07
    沮丧
    0.07
     anonymously
    0.07
    ณา
    0.07
    _URL
    0.07
    Act Density 0.239%

    No Known Activations