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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бан
    -0.07
    *.
    -0.07
    itos
    -0.06
    (add
    -0.06
    ‌های
    -0.06
    客
    -0.06
    .skill
    -0.06
    ��이
    -0.06
    _SCHED
    -0.06
    	fields
    -0.06
    POSITIVE LOGITS
     Awake
    0.06
     pretending
    0.06
     warming
    0.06
    izard
    0.06
     '%'
    0.06
     nullptr
    0.06
    ollen
    0.06
    Producer
    0.06
     yarar
    0.06
    	mouse
    0.06
    Act Density 0.002%

    No Known Activations