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

    Neuronpedia

    INDEX
    Explanations

    hand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forecasts
    -0.06
     compensation
    -0.06
    ули
    -0.06
     وص
    -0.06
    loom
    -0.06
    ories
    -0.06
    uber
    -0.06
    PROP
    -0.06
    \Test
    -0.06
    Aligned
    -0.06
    POSITIVE LOGITS
    (CharSequence
    0.07
     bande
    0.07
     libero
    0.07
     ningún
    0.06
     приготовить
    0.06
     ≥
    0.06
     cuerpo
    0.06
     Maison
    0.06
    ĩa
    0.06
    ripper
    0.06
    Act Density 0.009%

    No Known Activations