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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leeway
    1.32
     composure
    1.16
     predicament
    1.14
     propriety
    1.12
     patt
    1.10
     guarant
    1.09
     ull
    1.09
    ς
    1.08
    ्स
    1.07
     draggable
    1.07
    POSITIVE LOGITS
    in
    1.99
    n
    1.82
    x
    1.48
    ০
    1.45
    al
    1.42
    ar
    1.41
    on
    1.40
    it
    1.38
    an
    1.37
    ان
    1.37
    Act Density 0.194%

    No Known Activations