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

    Neuronpedia

    INDEX
    Explanations

    view on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Springs
    1.18
     Infants
    1.15
     Grâce
    1.13
     Institutes
    1.12
     Cats
    1.12
    న్నా
    1.10
     pleasures
    1.09
     recesses
    1.09
     Undoubtedly
    1.08
     Reverse
    1.07
    POSITIVE LOGITS
    বিএন
    1.33
    m
    1.32
    kým
    1.27
    ان
    1.26
    ن
    1.24
    o
    1.23
     berisi
    1.15
    yce
    1.14
    on
    1.13
    ӳ
    1.13
    Act Density 0.001%

    No Known Activations