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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >User
    -0.07
    dates
    -0.06
    Nice
    -0.06
    よ
    -0.06
     تخصص
    -0.06
    .o
    -0.06
    >Login
    -0.06
     Plenty
    -0.06
     DWORD
    -0.06
    _hpp
    -0.06
    POSITIVE LOGITS
     foundation
    0.07
    ů
    0.07
     hiện
    0.06
    增
    0.06
     Ansi
    0.06
    태
    0.06
    �
    0.06
     fund
    0.06
    _lv
    0.06
     expansive
    0.06
    Act Density 0.016%

    No Known Activations