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

    Neuronpedia

    INDEX
    Explanations

    identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Faith
    -0.06
    �
    -0.06
    xr
    -0.06
     четы
    -0.06
    getRepository
    -0.06
     rit
    -0.06
    Con
    -0.06
     researchers
    -0.06
     incr
    -0.06
    acet
    -0.06
    POSITIVE LOGITS
     віднов
    0.08
     Colomb
    0.07
    itung
    0.07
    ield
    0.07
     Identification
    0.07
    couz
    0.07
    fusion
    0.07
     시행
    0.07
    رفت
    0.06
     stabilize
    0.06
    Act Density 0.012%

    No Known Activations