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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    负面
    -0.07
    UPLE
    -0.06
    陲
    -0.06
    点钟
    -0.06
    Ⲉ
    -0.06
    utor
    -0.06
    Carl
    -0.06
    糟糕
    -0.06
    	CG
    -0.06
    感冒
    -0.06
    POSITIVE LOGITS
    >F
    0.07
     recession
    0.07
     forty
    0.07
    став
    0.07
     walls
    0.07
     그런데
    0.07
     maxY
    0.07
    (depend
    0.07
     Migration
    0.06
    Include
    0.06
    Act Density 0.000%

    No Known Activations