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

    Neuronpedia

    INDEX
    Explanations

    years in the 2010s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Robert
    -0.08
     خواه
    -0.07
    YTE
    -0.07
     moins
    -0.06
     hotter
    -0.06
     ضر
    -0.06
    力を
    -0.06
     createdAt
    -0.06
     WL
    -0.06
     royal
    -0.06
    POSITIVE LOGITS
     disturb
    0.07
     آخرین
    0.06
     muse
    0.06
    ARGIN
    0.06
    },↵
    0.06
    -trained
    0.06
    sound
    0.06
    .sale
    0.06
    unities
    0.06
    .emit
    0.06
    Act Density 0.005%

    No Known Activations