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

    Neuronpedia

    INDEX
    Explanations

    Designing and building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engagement
    -0.08
     tình
    -0.08
     histori
    -0.08
     mê
    -0.08
     lice
    -0.08
     poderoso
    -0.07
     ngày
    -0.07
    .slf
    -0.07
     če
    -0.07
     người
    -0.07
    POSITIVE LOGITS
     entrega
    0.09
    Entrega
    0.09
     Lieferung
    0.08
    pụta
    0.08
     indica
    0.07
    =q
    0.07
     liefern
    0.07
    مپ
    0.07
    Successfully
    0.07
     Basin
    0.07
    Act Density 0.038%

    No Known Activations