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

    Neuronpedia

    INDEX
    Explanations

    Python list operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    机场
    0.44
    🐟
    0.43
    🐠
    0.39
    骼
    0.38
    мыш
    0.37
     recur
    0.37
     distinctly
    0.35
     Branches
    0.35
    axter
    0.35
    Airport
    0.35
    POSITIVE LOGITS
     culinary
    0.43
     viscose
    0.43
     steam
    0.41
     violently
    0.41
     moulds
    0.40
    द्वितीय
    0.40
     атаку
    0.40
     Kharkiv
    0.39
     යුතු
    0.39
     benzoic
    0.39
    Act Density 0.000%

    No Known Activations