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

    Neuronpedia

    INDEX
    Explanations

    act or behave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WP
    0.57
     WP
    0.57
    VP
    0.49
    mpa
    0.48
    Moves
    0.47
     MPA
    0.47
    Managing
    0.47
    Thoughts
    0.47
     PowerPoint
    0.46
    GitHub
    0.46
    POSITIVE LOGITS
     нефте
    0.52
    ».
    0.50
     гео
    0.50
     سپس
    0.50
    ărilor
    0.48
     speeches
    0.46
    闼
    0.46
     universes
    0.46
    伲
    0.46
    빗
    0.46
    Act Density 0.000%

    No Known Activations