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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    735
    -0.08
    larındaki
    -0.07
     налог
    -0.07
     NG
    -0.07
     auctions
    -0.06
    ırlar
    -0.06
    ura
    -0.06
    .CreateDirectory
    -0.06
    다면
    -0.06
    _agents
    -0.06
    POSITIVE LOGITS
     मल
    0.06
    족
    0.06
     منزل
    0.06
     projev
    0.06
    interopRequireDefault
    0.06
     Executors
    0.06
     Bring
    0.06
    �回
    0.06
    Bring
    0.06
     millis
    0.06
    Act Density 0.022%

    No Known Activations