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

    Neuronpedia

    INDEX
    Explanations

    1-800-THE-LOST

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sole
    0.40
     phy
    0.39
    ilit
    0.39
     Bella
    0.38
    اويه
    0.38
    齙
    0.38
     Diff
    0.37
    estine
    0.37
    飜
    0.37
    sole
    0.37
    POSITIVE LOGITS
    Wish
    0.39
     빅
    0.38
    Big
    0.36
     Big
    0.35
    Vijay
    0.35
    越
    0.35
    SearchBar
    0.34
    BAD
    0.34
    使其
    0.34
     tac
    0.34
    Act Density 0.005%

    No Known Activations