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

    Neuronpedia

    INDEX
    Explanations

    Python code and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unions
    0.43
     variant
    0.39
     mutations
    0.38
     batches
    0.38
    JSON
    0.37
     corporations
    0.37
     variants
    0.37
     collisions
    0.37
    php
    0.36
     JavaScript
    0.36
    POSITIVE LOGITS
     strolled
    0.48
     Sita
    0.47
     Payton
    0.47
     Dorothy
    0.45
     نے
    0.45
     också
    0.45
    凭
    0.45
     walked
    0.44
     Leah
    0.44
     můžete
    0.44
    Act Density 0.000%

    No Known Activations