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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	nil
    -0.07
     panic
    -0.07
     Convert
    -0.07
     Aug
    -0.07
    site
    -0.07
    -sized
    -0.06
     clutter
    -0.06
     avocado
    -0.06
     Resort
    -0.06
    ,&
    -0.06
    POSITIVE LOGITS
    iş
    0.07
     youngsters
    0.07
    _AB
    0.07
    alie
    0.06
     الاع
    0.06
    олі
    0.06
    िस
    0.06
     ル
    0.06
     CEL
    0.06
     ود
    0.06
    Act Density 0.016%

    No Known Activations