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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adder
    -0.07
    ''
    -0.07
    _BS
    -0.07
    教案
    -0.07
     conductor
    -0.07
    hits
    -0.07
    涅
    -0.07
     formations
    -0.07
    给孩子
    -0.07
     unordered
    -0.07
    POSITIVE LOGITS
     Evangel
    0.06
     Goose
    0.06
    yla
    0.06
     PvP
    0.06
    dont
    0.06
     handled
    0.06
    将在
    0.06
     WebSocket
    0.06
     fleets
    0.06
     arrog
    0.06
    Act Density 0.018%

    No Known Activations