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

    Neuronpedia

    INDEX
    Explanations

    find all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Notes
    0.41
     GREAT
    0.40
     GRA
    0.38
     Great
    0.38
     வெறு
    0.38
     LIT
    0.38
     পুনঃ
    0.38
     &
    0.38
     Est
    0.37
     Opinion
    0.37
    POSITIVE LOGITS
    ២
    0.47
    ulé
    0.43
    hile
    0.41
    ⊡
    0.41
    ⒈
    0.41
    uleiro
    0.40
    Xr
    0.40
    งิน
    0.40
     Landes
    0.39
     получать
    0.39
    Act Density 0.000%

    No Known Activations