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

    Neuronpedia

    INDEX
    Explanations

    reptiles and snakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eureka
    0.93
     Mpc
    0.93
    萩
    0.93
     eureka
    0.84
    Eureka
    0.81
     Puch
    0.77
    苫
    0.76
    侑
    0.76
     suffrage
    0.75
    ុម
    0.74
    POSITIVE LOGITS
     snake
    3.25
     snakes
    3.13
     Snake
    2.94
    Snake
    2.83
     Snakes
    2.78
     reptile
    2.71
    snake
    2.67
     serpent
    2.59
     reptiles
    2.54
    🐍
    2.50
    Act Density 0.145%

    No Known Activations