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

    Neuronpedia

    INDEX
    Explanations

    graduation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	layout
    -0.06
    <Menu
    -0.06
    (subject
    -0.06
    мена
    -0.06
     firstName
    -0.06
    fair
    -0.06
     мона
    -0.06
    }">↵
    -0.06
     =",
    -0.06
     א
    -0.06
    POSITIVE LOGITS
     mpi
    0.07
    Ik
    0.07
    alarının
    0.06
    YouTube
    0.06
    gregated
    0.06
    ;b
    0.06
     arrayList
    0.06
     Improved
    0.06
    itter
    0.06
     likewise
    0.06
    Act Density 0.029%

    No Known Activations