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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ETF
    -0.08
     spo
    -0.07
     zase
    -0.07
     femme
    -0.07
    ica
    -0.07
    empo
    -0.06
    (GameObject
    -0.06
    tu
    -0.06
     yo
    -0.06
     asyncio
    -0.06
    POSITIVE LOGITS
    right
    0.09
    /register
    0.07
     abilities
    0.06
    ivering
    0.06
    five
    0.06
     mell
    0.06
    plevel
    0.06
    ifference
    0.06
    ]</
    0.06
    골
    0.06
    Act Density 0.007%

    No Known Activations