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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    短
    -0.06
    Attempts
    -0.06
    Sometimes
    -0.06
    ůležit
    -0.06
     Census
    -0.06
    Scan
    -0.06
     inhabitants
    -0.06
     cerc
    -0.06
    iren
    -0.06
     claro
    -0.06
    POSITIVE LOGITS
     compose
    0.07
    ине
    0.07
    alement
    0.06
     Padding
    0.06
    quip
    0.06
     ↵↵
    0.06
     }↵↵
    0.06
    	Start
    0.06
    ері
    0.06
     VStack
    0.06
    Act Density 0.076%

    No Known Activations