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

    Neuronpedia

    INDEX
    Explanations

    Flask code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PAIR
    -0.07
     C
    -0.06
    _BT
    -0.06
     boca
    -0.06
     století
    -0.06
    ερι
    -0.06
     Teddy
    -0.06
    _offsets
    -0.06
    ียร
    -0.06
    BarItem
    -0.06
    POSITIVE LOGITS
     lands
    0.07
     pumpkin
    0.07
    няя
    0.06
    /gif
    0.06
     fasc
    0.06
    natural
    0.06
     Directive
    0.06
     quar
    0.06
    .sap
    0.06
    ійської
    0.06
    Act Density 0.001%

    No Known Activations