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

    Neuronpedia

    INDEX
    Explanations

    without a condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anything
    0.59
    Anything
    0.56
     comienzan
    0.55
     anything
    0.55
     empiezan
    0.50
     Anything
    0.48
     quelconque
    0.47
     puisqu
    0.47
    Hand
    0.46
     FIGURE
    0.46
    POSITIVE LOGITS
     fanfare
    0.53
     recourse
    0.47
     resorting
    0.46
     without
    0.45
    without
    0.45
     햇
    0.43
     ущер
    0.43
    彷
    0.43
     Bih
    0.43
     repercussions
    0.42
    Act Density 0.018%

    No Known Activations