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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doping
    -0.07
     antic
    -0.06
    CPP
    -0.06
     plaque
    -0.06
    EXIT
    -0.06
    辐
    -0.06
    梌
    -0.06
     prejud
    -0.06
     fitted
    -0.06
    adb
    -0.06
    POSITIVE LOGITS
    сла
    0.08
    _>
    0.08
    -->↵↵
    0.08
     ?>↵↵↵
    0.07
    🧡
    0.07
     catcher
    0.07
     chùa
    0.07
    🕳
    0.07
    🎼
    0.07
    这是我
    0.07
    Act Density 0.013%

    No Known Activations