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

    Neuronpedia

    INDEX
    Explanations

    bracht

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trust
    -0.07
    	game
    -0.06
     fps
    -0.06
    ero
    -0.06
    OrNil
    -0.06
    ihilation
    -0.06
    -language
    -0.06
    }",
    -0.06
    ız
    -0.06
     hostile
    -0.06
    POSITIVE LOGITS
    ़ों
    0.06
     син
    0.06
    .pair
    0.06
     DeepCopy
    0.06
     '-
    0.06
     επί
    0.06
    егор
    0.06
     Ради
    0.06
    uyển
    0.06
    yyval
    0.06
    Act Density 0.000%

    No Known Activations