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

    Neuronpedia

    INDEX
    Explanations

    Math/Scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    35
    -0.07
     OWNER
    -0.07
    _bulk
    -0.07
    告诉
    -0.07
     Toyota
    -0.06
    来说
    -0.06
     donne
    -0.06
     ()↵↵
    -0.06
     конкрет
    -0.06
    ＼:
    -0.06
    POSITIVE LOGITS
    unders
    0.07
     pe
    0.07
    offer
    0.06
    bis
    0.06
    _payment
    0.06
    makt
    0.06
    kách
    0.06
    aji
    0.06
     безопас
    0.06
    saida
    0.06
    Act Density 0.029%

    No Known Activations