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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -backed
    -0.09
    不过
    -0.08
     rollback
    -0.08
    登陆
    -0.08
     നവ
    -0.08
     WARNING
    -0.08
     ورو
    -0.08
     culmin
    -0.08
     zaměst
    -0.08
     vetted
    -0.08
    POSITIVE LOGITS
     textbooks
    0.12
     textbook
    0.11
     convention
    0.11
     confusion
    0.10
     conventions
    0.10
     notation
    0.09
     mathematic
    0.09
     folks
    0.09
     approaches
    0.09
     confusing
    0.08
    Act Density 0.022%

    No Known Activations