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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .’↵↵
    -0.08
     BOT
    -0.07
    ?“↵↵
    -0.07
    	write
    -0.06
     механіз
    -0.06
     büyük
    -0.06
    .fromRGBO
    -0.06
    .gz
    -0.06
     zinc
    -0.06
    阻
    -0.06
    POSITIVE LOGITS
     full
    0.10
     FULL
    0.08
     Full
    0.08
    Full
    0.07
     completa
    0.07
     lineup
    0.06
    razil
    0.06
    full
    0.06
    Attrs
    0.06
     Dhabi
    0.06
    Act Density 0.010%

    No Known Activations