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
    August
    -0.07
    нули
    -0.06
    ع
    -0.06
    :.
    -0.06
    .POST
    -0.06
     rearr
    -0.06
     deck
    -0.06
     bus
    -0.06
    غاز
    -0.06
     Access
    -0.06
    POSITIVE LOGITS
     quản
    0.07
     Before
    0.06
     outbreaks
    0.06
    LEV
    0.06
     unwind
    0.06
    σο
    0.06
    _TB
    0.06
    _Update
    0.06
    Rep
    0.06
     Би
    0.06
    Act Density 0.000%

    No Known Activations