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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saturation
    -0.08
    Loading
    -0.07
    なが
    -0.06
     Ros
    -0.06
     Maker
    -0.06
     cabinets
    -0.06
    (strcmp
    -0.06
     customers
    -0.06
    Lewis
    -0.06
     jumps
    -0.06
    POSITIVE LOGITS
    秘
    0.06
    _Two
    0.06
     nhằm
    0.06
    ơm
    0.06
    _wr
    0.06
    ordinary
    0.06
    饮
    0.06
    fred
    0.06
     места
    0.06
    ˆ
    0.06
    Act Density 0.030%

    No Known Activations