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

    Neuronpedia

    INDEX
    Explanations

    Disagreement/critique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LC
    -0.07
     Expect
    -0.06
    _-_
    -0.06
    ):-
    -0.06
     Stuart
    -0.06
     Jenna
    -0.06
     estoy
    -0.06
    茶
    -0.06
    Chrome
    -0.06
     naš
    -0.06
    POSITIVE LOGITS
     acquisition
    0.07
     mand
    0.06
     Built
    0.06
     Contracts
    0.06
     play
    0.06
     mechanically
    0.06
     exclude
    0.06
     갤로그로
    0.06
     Волод
    0.06
     Μέ
    0.06
    Act Density 0.042%

    No Known Activations