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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aguay
    -0.07
    On
    -0.07
    IID
    -0.07
     داشتن
    -0.07
    HDATA
    -0.06
     policing
    -0.06
     UserRole
    -0.06
    การณ
    -0.06
    -but
    -0.06
     on
    -0.06
    POSITIVE LOGITS
     Farmers
    0.08
    *)&
    0.07
    .toolbar
    0.07
     artisans
    0.07
    ารย
    0.06
    .GetMapping
    0.06
     должно
    0.06
     surprisingly
    0.06
    ())[
    0.06
    超过
    0.06
    Act Density 0.058%

    No Known Activations