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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clintons
    -0.07
     факт
    -0.07
     panorama
    -0.06
    ilden
    -0.06
    egrity
    -0.06
    rometer
    -0.06
    یه
    -0.06
    ับน
    -0.06
    ZX
    -0.06
     belts
    -0.06
    POSITIVE LOGITS
    ,output
    0.07
    <R
    0.07
     AMAZ
    0.07
     Mostly
    0.07
     Володими
    0.06
     TOUCH
    0.06
    missing
    0.06
    <bool
    0.06
    [root
    0.06
     reprint
    0.06
    Act Density 0.016%

    No Known Activations