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

    Neuronpedia

    INDEX
    Explanations

    `snake.py` code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğim
    0.41
    ğı
    0.40
     واقعات
    0.39
     consiguió
    0.39
    Pedidos
    0.39
    np
    0.38
    concret
    0.36
    седнев
    0.36
    partitions
    0.36
    şa
    0.35
    POSITIVE LOGITS
     rib
    0.39
     dare
    0.36
     ബാറ്റ
    0.35
     ribbon
    0.35
     Rear
    0.34
    Lamb
    0.34
    aterally
    0.34
     DISC
    0.34
     chines
    0.33
     Quality
    0.33
    Act Density 0.000%

    No Known Activations