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

    Neuronpedia

    INDEX
    Explanations

    jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    팔
    -0.07
    EqualTo
    -0.06
     mommy
    -0.06
     Dam
    -0.06
    跨
    -0.06
    끼
    -0.06
     силы
    -0.06
    htable
    -0.06
    265
    -0.06
     Stard
    -0.06
    POSITIVE LOGITS
     угл
    0.07
     DCHECK
    0.07
     Moines
    0.07
    >{
    0.06
     اسلام
    0.06
    }`
    0.06
    	InputStream
    0.06
    
    0.06
    ]$
    0.06
    ][$
    0.06
    Act Density 0.044%

    No Known Activations