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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    und
    -0.08
    otto
    -0.07
     wind
    -0.07
    raid
    -0.06
    办公室
    -0.06
     reforms
    -0.06
     Approved
    -0.06
     зрения
    -0.06
    诏
    -0.06
    umas
    -0.06
    POSITIVE LOGITS
     bricks
    0.09
    =tmp
    0.07
     cake
    0.07
    年之久
    0.07
     impoverished
    0.07
    糖果
    0.07
     Create
    0.07
     piel
    0.07
    环绕
    0.07
     Equals
    0.07
    Act Density 0.187%

    No Known Activations