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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spe
    -0.07
    -minus
    -0.07
    thresh
    -0.06
     Fischer
    -0.06
     tet
    -0.06
    國
    -0.06
     stale
    -0.06
     Χ
    -0.06
     Hiro
    -0.06
     Über
    -0.06
    POSITIVE LOGITS
    -lived
    0.08
    liğin
    0.07
    /)
    0.07
    _Send
    0.07
    )},
    0.06
     optical
    0.06
    }")
    0.06
     volatility
    0.06
     П
    0.06
    нообраз
    0.06
    Act Density 0.008%

    No Known Activations