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

    Neuronpedia

    INDEX
    Explanations

    understanding context and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    black
    0.43
    specified
    0.43
    use
    0.43
    va
    0.43
    usher
    0.43
    over
    0.42
    up
    0.42
    bright
    0.41
    generating
    0.41
    ice
    0.41
    POSITIVE LOGITS
     Moż
    0.40
     অনি
    0.39
     unmistakable
    0.39
     δια
    0.39
     Tamm
    0.39
    🄰
    0.39
     STORIES
    0.38
     আপন
    0.38
    𒊏
    0.38
     inexplicable
    0.38
    Act Density 0.001%

    No Known Activations