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

    Neuronpedia

    INDEX
    Explanations

    essential key concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ात
    0.81
    idak
    0.73
    urally
    0.70
    முற
    0.69
    。(
    0.67
     முற
    0.67
     Xác
    0.66
    igts
    0.66
    powied
    0.65
     उदा
    0.65
    POSITIVE LOGITS
     enemy
    1.30
     enemies
    1.16
    enemy
    1.16
     contagious
    1.15
    Enemy
    1.08
     rampant
    1.08
     overrated
    1.02
    enemies
    1.02
     mantra
    1.00
     contag
    0.99
    Act Density 0.169%

    No Known Activations