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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лів
    -0.08
    watch
    -0.06
    луата
    -0.06
    ㎡
    -0.06
    очные
    -0.06
     skirt
    -0.06
    fname
    -0.06
     computation
    -0.06
     Roth
    -0.06
     true
    -0.06
    POSITIVE LOGITS
     přeh
    0.07
    	dis
    0.07
    .removeAttribute
    0.07
    deniz
    0.06
     two
    0.06
    _controls
    0.06
    PN
    0.06
    ALSE
    0.06
    (ListNode
    0.06
    -three
    0.06
    Act Density 0.021%

    No Known Activations