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

    Neuronpedia

    INDEX
    Explanations

    self-defense and self-positioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.69
    '
    0.61
    (
    0.57
    ’
    0.55
    -
    0.51
    :
    0.51
    ní
    0.51
    EN
    0.50
    AD
    0.50
    我
    0.49
    POSITIVE LOGITS
     democracies
    0.50
     or
    0.49
     has
    0.46
     ஒவ்வொரு
    0.45
     aerosol
    0.44
     stripped
    0.43
     thermonuclear
    0.43
     cardiovascular
    0.43
    ꞎ
    0.43
     بر
    0.42
    Act Density 0.006%

    No Known Activations