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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dahil
    -0.07
    _HORIZONTAL
    -0.06
     players
    -0.06
    .ul
    -0.06
    ductive
    -0.06
     учрежд
    -0.06
     Ur
    -0.06
    Sports
    -0.06
    _mid
    -0.06
     vocalist
    -0.06
    POSITIVE LOGITS
     cookie
    0.06
     брос
    0.06
    UNCTION
    0.06
     Homemade
    0.06
     instantly
    0.06
     Backpack
    0.06
     Brother
    0.06
    umsuz
    0.06
    	MPI
    0.06
     choke
    0.06
    Act Density 0.006%

    No Known Activations