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

    Neuronpedia

    INDEX
    Explanations

    parsing data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toString
    0.37
     ð
    0.37
     Offline
    0.36
     লক
    0.36
    _{-\
    0.35
     Attribution
    0.35
     concurrency
    0.35
     حلقه
    0.35
    ICLES
    0.34
     রাখুন
    0.34
    POSITIVE LOGITS
    phi
    0.46
     ■
    0.45
    ■
    0.44
    Agr
    0.43
    odend
    0.39
    ピ
    0.38
    ピーク
    0.38
    ometrical
    0.36
    Kw
    0.35
    acheter
    0.35
    Act Density 0.001%

    No Known Activations