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

    Neuronpedia

    INDEX
    Explanations

    Multi-course meals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exposures
    -0.07
     Encoder
    -0.07
    Month
    -0.07
     Cycle
    -0.06
     throne
    -0.06
     inference
    -0.06
     voters
    -0.06
     ادبی
    -0.06
     movies
    -0.06
    	to
    -0.06
    POSITIVE LOGITS
     typingsSlinky
    0.07
    .Guid
    0.07
     typingsJapgolly
    0.07
    eği
    0.07
     asyncio
    0.06
    abilecek
    0.06
     بي
    0.06
    ।↵
    0.06
     Simone
    0.06
    搭
    0.06
    Act Density 0.041%

    No Known Activations