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

    Neuronpedia

    INDEX
    Explanations

    flaws/negative results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Venta
    -0.08
    ं
    -0.07
    .SelectedIndexChanged
    -0.07
    hir
    -0.06
     Soviets
    -0.06
    ooky
    -0.06
    ;};↵
    -0.06
     nik
    -0.06
    ینگ
    -0.06
    alardan
    -0.05
    POSITIVE LOGITS
     mindset
    0.08
    ]
↵
    0.06
     intestine
    0.06
     '?
    0.06
    (update
    0.06
     ensures
    0.06
     "--
    0.06
     olduğunu
    0.06
     discour
    0.06
     Line
    0.06
    Act Density 0.234%

    No Known Activations