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

    Neuronpedia

    INDEX
    Explanations

    chord

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polyester
    -0.08
     protective
    -0.08
     savedInstanceState
    -0.07
     EVAL
    -0.07
    抗日
    -0.07
    .§
    -0.07
    防腐
    -0.07
     noteworthy
    -0.07
    俱
    -0.07
     התב
    -0.07
    POSITIVE LOGITS
    上班族
    0.07
    lider
    0.07
    gypt
    0.07
    덟
    0.07
    <pcl
    0.07
    	left
    0.07
    lots
    0.07
     shrine
    0.07
    邸
    0.07
     brasile
    0.07
    Act Density 0.002%

    No Known Activations