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

    Neuronpedia

    INDEX
    Explanations

    fish species

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turtle
    0.42
     Turtle
    0.40
     reptile
    0.40
     މި
    0.40
     tortoise
    0.39
     reptiles
    0.39
    莪
    0.39
    otia
    0.38
     insect
    0.38
    ளிட
    0.38
    POSITIVE LOGITS
     kis
    0.41
     masu
    0.39
     Kiz
    0.38
     Dolly
    0.38
     Richardson
    0.38
    Richardson
    0.37
    平方
    0.36
     bair
    0.36
    sair
    0.36
    少なく
    0.36
    Act Density 0.001%

    No Known Activations