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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीब
    -0.07
     armored
    -0.07
     invaluable
    -0.07
     metabolism
    -0.07
    Bern
    -0.06
    Mal
    -0.06
    _rhs
    -0.06
    GX
    -0.06
    OPT
    -0.06
     Pregn
    -0.06
    POSITIVE LOGITS
     simp
    0.07
    	change
    0.07
     dejar
    0.06
    대행
    0.06
     hecho
    0.06
     нав
    0.06
     диаг
    0.06
     surge
    0.06
     carved
    0.06
     intéress
    0.06
    Act Density 0.016%

    No Known Activations