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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ខ្ញ
    0.41
     miatt
    0.41
     réunis
    0.41
     çiçek
    0.41
    笉
    0.41
    ilere
    0.40
    လား
    0.39
    illons
    0.39
    テープ
    0.39
    lytres
    0.39
    POSITIVE LOGITS
     strives
    0.36
     heave
    0.35
    s
    0.33
     helps
    0.33
     type
    0.32
     timings
    0.32
     Course
    0.31
     Help
    0.31
     benefits
    0.31
     Offer
    0.31
    Act Density 0.003%

    No Known Activations