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

    Neuronpedia

    INDEX
    Explanations

    Programming code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    claimer
    -0.07
    arken
    -0.06
    ),
    -0.06
    (problem
    -0.06
    ”),
    -0.06
    )،
    -0.06
    ([(
    -0.06
    addafi
    -0.06
     feasibility
    -0.06
    %),
    -0.06
    POSITIVE LOGITS
     installation
    0.07
    (start
    0.06
    .returnValue
    0.06
     що
    0.06
     benchmark
    0.06
    논
    0.06
     USA
    0.06
     bağ
    0.06
    月
    0.06
     ağır
    0.06
    Act Density 0.095%

    No Known Activations