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

    Neuronpedia

    INDEX
    Explanations

    summaries and previews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opard
    -0.08
     Владим
    -0.07
    绿
    -0.07
    �
    -0.07
     playful
    -0.06
     Adds
    -0.06
    自然灾害
    -0.06
    ackers
    -0.06
    udden
    -0.06
    -host
    -0.06
    POSITIVE LOGITS
    不错
    0.07
     properly
    0.07
     GRID
    0.07
    سان
    0.07
     данной
    0.07
    .bin
    0.07
    -wrapper
    0.07
     المنتخب
    0.07
    link
    0.07
    _clip
    0.07
    Act Density 0.019%

    No Known Activations