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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '},
    -0.07
     counted
    -0.07
     Müslüman
    -0.07
     achieved
    -0.07
    (System
    -0.06
    TypeID
    -0.06
    獸
    -0.06
     estimated
    -0.06
    );↵↵↵↵↵
    -0.06
    (sel
    -0.06
    POSITIVE LOGITS
    柱
    0.07
    bag
    0.07
    wers
    0.07
    alchemy
    0.07
    GetX
    0.07
    emb
    0.07
     tras
    0.06
    acers
    0.06
    GCC
    0.06
    asca
    0.06
    Act Density 0.037%

    No Known Activations