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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (LP
    -0.07
    .Printf
    -0.06
     plagiar
    -0.06
    思想
    -0.06
    Manchester
    -0.06
     abol
    -0.06
     restraining
    -0.06
     ăn
    -0.06
    (exit
    -0.06
     Gate
    -0.06
    POSITIVE LOGITS
    ebilir
    0.07
     hızlı
    0.06
    say
    0.06
    Renderer
    0.06
    ीण
    0.06
    (cancel
    0.06
    息
    0.06
    leccion
    0.06
    tags
    0.06
    슴
    0.06
    Act Density 0.000%

    No Known Activations