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

    Neuronpedia

    INDEX
    Explanations

    put

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URAL
    -0.07
     multis
    -0.06
     feather
    -0.06
    cairo
    -0.06
    建筑
    -0.06
     warehouses
    -0.06
    _median
    -0.06
    lick
    -0.06
     markers
    -0.06
    amer
    -0.06
    POSITIVE LOGITS
    omentum
    0.08
    进
    0.06
    .dump
    0.06
    .sul
    0.06
     Spart
    0.06
     trạng
    0.06
    僕
    0.06
     DFA
    0.06
     probí
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations