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

    Neuronpedia

    INDEX
    Explanations

    tour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пл
    -0.07
    �
    -0.07
    906
    -0.07
    (pid
    -0.06
    445
    -0.06
    .addSubview
    -0.06
     بد
    -0.06
     poj
    -0.06
    443
    -0.06
    Snippet
    -0.06
    POSITIVE LOGITS
     criticised
    0.07
     فإن
    0.06
     driving
    0.06
    	title
    0.06
    balls
    0.06
     kept
    0.06
    .Rectangle
    0.06
     realities
    0.06
     oppos
    0.06
     heavy
    0.06
    Act Density 0.040%

    No Known Activations