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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بیر
    -0.07
     Romance
    -0.07
     fran
    -0.07
    Popular
    -0.06
    -video
    -0.06
     Statistics
    -0.06
     Whitney
    -0.06
     Fleming
    -0.06
     analytic
    -0.06
     jer
    -0.06
    POSITIVE LOGITS
    ControlEvents
    0.08
    ===↵
    0.07
    .payload
    0.07
    _utf
    0.06
    (Pointer
    0.06
     معنی
    0.06
     chipset
    0.06
    ConstraintMaker
    0.06
    ुए
    0.06
    (pg
    0.06
    Act Density 0.015%

    No Known Activations