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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diese
    -0.06
     предпри
    -0.06
     виснов
    -0.06
     Ά
    -0.06
    оду
    -0.06
     Ama
    -0.06
    IMPORTANT
    -0.06
    Sem
    -0.06
     unas
    -0.06
     abbreviation
    -0.06
    POSITIVE LOGITS
     experimented
    0.07
    �
    0.07
    (ins
    0.07
    .graph
    0.06
    eneric
    0.06
    Aligned
    0.06
    (undefined
    0.06
    Gem
    0.06
    .Tasks
    0.06
    	create
    0.06
    Act Density 0.001%

    No Known Activations