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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    players
    -0.06
    失败
    -0.06
     injured
    -0.06
    Stop
    -0.06
     withheld
    -0.06
     mate
    -0.06
    	world
    -0.06
     pal
    -0.06
     merciless
    -0.06
    toBeDefined
    -0.06
    POSITIVE LOGITS
     tarihi
    0.07
    งน
    0.07
    'є
    0.07
    άννης
    0.07
    ‌ن
    0.07
    ove
    0.06
    eea
    0.06
    August
    0.06
     August
    0.06
    ินการ
    0.06
    Act Density 0.020%

    No Known Activations