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

    Neuronpedia

    INDEX
    Explanations

    Holding bodily functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َه
    -0.07
     TIME
    -0.07
     nhưng
    -0.07
    boat
    -0.07
    (size
    -0.06
    bounded
    -0.06
     Time
    -0.06
     murdering
    -0.06
     squared
    -0.06
     cols
    -0.06
    POSITIVE LOGITS
     manufact
    0.07
    ="#"><
    0.07
     Himal
    0.06
    _Tick
    0.06
     contrario
    0.06
    ImplOptions
    0.06
     zad
    0.06
    .Strict
    0.06
    .Solid
    0.06
     جنسی
    0.06
    Act Density 0.007%

    No Known Activations