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

    Neuronpedia

    INDEX
    Explanations

    forget

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    更适合
    -0.08
    iggs
    -0.07
    	stack
    -0.07
    CNN
    -0.07
     lava
    -0.07
    正因为
    -0.07
     duy
    -0.07
     Duffy
    -0.07
     Lena
    -0.07
    Ajax
    -0.07
    POSITIVE LOGITS
     הממשלה
    0.08
    منتديات
    0.07
    (TypeError
    0.07
     OnDestroy
    0.06
    _TOOLTIP
    0.06
    .cmd
    0.06
    .Count
    0.06
    imest
    0.06
     Ci
    0.06
    [M
    0.06
    Act Density 0.011%

    No Known Activations