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
    还原
    -0.07
     placement
    -0.07
     Pare
    -0.06
     lamb
    -0.06
    RY
    -0.06
    Now
    -0.06
    ocratic
    -0.06
    raz
    -0.06
    大陆
    -0.06
    kształ
    -0.06
    POSITIVE LOGITS
    .schedule
    0.08
    [:-
    0.08
    /fs
    0.07
    _DRAW
    0.07
    demo
    0.07
    탯
    0.07
    odule
    0.07
     Polit
    0.07
    /crypto
    0.06
     condominium
    0.06
    Act Density 0.093%

    No Known Activations