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

    Neuronpedia

    INDEX
    Explanations

    Major events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     쇼
    -0.07
     orchestr
    -0.06
     reh
    -0.06
     tête
    -0.06
     κό
    -0.06
     πλα
    -0.06
    QRSTUVWXYZ
    -0.06
     yeah
    -0.06
    ιά
    -0.06
     includes
    -0.06
    POSITIVE LOGITS
     IICIII
    0.07
    ):?>↵
    0.06
     vybav
    0.06
    ]]];↵
    0.06
    _SLOT
    0.06
    0.06
     optimal
    0.06
    usalem
    0.06
     Mont
    0.06
     Lantern
    0.06
    Act Density 0.048%

    No Known Activations