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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     byt
    -0.08
    กรม
    -0.07
     �
    -0.06
    ，她
    -0.06
    Coupon
    -0.06
     anecdotes
    -0.06
     NATIONAL
    -0.06
     imposition
    -0.06
    Nat
    -0.06
    列表
    -0.06
    POSITIVE LOGITS
    raph
    0.07
     airl
    0.07
    -secret
    0.06
     Assumes
    0.06
     결정
    0.06
     bás
    0.06
     realize
    0.06
     niż
    0.06
     CALLBACK
    0.06
     STDCALL
    0.06
    Act Density 0.003%

    No Known Activations