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
     Louis
    -0.08
     виник
    -0.07
    	StringBuilder
    -0.07
    ↵    ↵    ↵
    -0.06
     sorting
    -0.06
     TODO
    -0.06
    	assertThat
    -0.06
    에는
    -0.06
     water
    -0.06
    ıştır
    -0.06
    POSITIVE LOGITS
     прик
    0.07
    .edit
    0.06
     pronounced
    0.06
     Bri
    0.06
     neighborhoods
    0.06
    POSIT
    0.06
     Property
    0.06
     quir
    0.06
     parody
    0.06
     인정
    0.06
    Act Density 0.058%

    No Known Activations