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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ше
    -0.07
     abaixo
    -0.07
    Board
    -0.07
    LOB
    -0.06
    My
    -0.06
    Vo
    -0.06
    .terminate
    -0.06
     αυτή
    -0.06
    _TO
    -0.06
    Women
    -0.06
    POSITIVE LOGITS
     Init
    0.07
     inund
    0.07
     Cellular
    0.06
     uncle
    0.06
     Palin
    0.06
     chili
    0.06
     punch
    0.06
    .*;↵
    0.06
     Vincent
    0.06
    ⠀⠀
    0.06
    Act Density 0.001%

    No Known Activations