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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Successfully
    -0.07
     visitors
    -0.07
     benz
    -0.06
    �
    -0.06
    錄
    -0.06
    早
    -0.06
    实验
    -0.06
    axy
    -0.06
    	client
    -0.06
    Stories
    -0.06
    POSITIVE LOGITS
    _given
    0.07
     Pf
    0.07
     ard
    0.06
    .sulake
    0.06
     ►
    0.06
    Abb
    0.06
     Btn
    0.06
     žádný
    0.06
    Equality
    0.06
    Semaphore
    0.06
    Act Density 0.009%

    No Known Activations