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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thomson
    -0.09
     Millions
    -0.08
     grassroots
    -0.07
    三分
    -0.07
    非常
    -0.07
    AAA
    -0.06
    .appendChild
    -0.06
     продолж
    -0.06
    REFERRED
    -0.06
    岭南
    -0.06
    POSITIVE LOGITS
    яем
    0.08
    _hard
    0.07
    _ot
    0.07
    -St
    0.07
    態
    0.07
    AE
    0.07
    емые
    0.07
    _th
    0.07
    :t
    0.06
    퇴
    0.06
    Act Density 0.001%

    No Known Activations