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

    Neuronpedia

    INDEX
    Explanations

    snake and serpent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Leeds
    0.44
     barista
    0.41
     Loretta
    0.41
    Leeds
    0.41
     فلسطینی
    0.40
     aerosols
    0.40
     Flanders
    0.40
     धरो
    0.39
    ignon
    0.39
     userData
    0.39
    POSITIVE LOGITS
     snake
    3.48
     snakes
    3.17
    Snake
    3.11
    蛇
    3.09
     Snake
    3.05
    snake
    3.00
     serpent
    2.84
     Snakes
    2.78
    🐍
    2.59
     serp
    2.56
    Act Density 0.049%

    No Known Activations