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

    Neuronpedia

    INDEX
    Explanations

    Name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roosevelt
    -0.07
    Zh
    -0.06
     Evil
    -0.06
     appart
    -0.06
    .adapters
    -0.06
    993
    -0.06
     RL
    -0.06
    ậ
    -0.06
     handlers
    -0.06
    buzz
    -0.06
    POSITIVE LOGITS
    Legendary
    0.07
    	className
    0.06
     лим
    0.06
     PAGE
    0.06
     administering
    0.06
     createElement
    0.06
     Annex
    0.06
    puty
    0.06
     className
    0.06
     торгов
    0.06
    Act Density 0.032%

    No Known Activations