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

    Neuronpedia

    INDEX
    Explanations

    输出

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acceler
    -0.09
     expér
    -0.08
     accelerator
    -0.08
    Acceler
    -0.08
     soft
    -0.07
    arten
    -0.07
    ernel
    -0.07
     expériment
    -0.07
     accelerate
    -0.07
     flames
    -0.07
    POSITIVE LOGITS
     megfe
    0.08
    お願いします
    0.08
    Ready
    0.08
     строго
    0.08
     бү
    0.08
     మా
    0.08
     borne
    0.08
     વિભાગ
    0.08
     obligación
    0.08
     READY
    0.08
    Act Density 0.073%

    No Known Activations