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

    Neuronpedia

    INDEX
    Explanations

    CORS originsCORS allow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wytr
    0.46
     stabile
    0.45
     stabilization
    0.41
     вершины
    0.41
     stabilized
    0.39
    Stabil
    0.39
     تجه
    0.39
     உருவா
    0.39
     верши
    0.38
     datth
    0.38
    POSITIVE LOGITS
    Allow
    1.02
     Allow
    1.00
     Allowing
    0.98
     allow
    0.96
     CORS
    0.95
    allow
    0.95
    允許
    0.95
     allowing
    0.93
     ALLOW
    0.93
    允许
    0.91
    Act Density 0.024%

    No Known Activations