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

    Neuronpedia

    INDEX
    Explanations

    variable or property access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StillWater
    0.41
    痱
    0.37
    孅
    0.37
    طع
    0.36
    一群
    0.35
     مصرف
    0.35
     फंक्शन
    0.34
     Гуляць
    0.34
     Jednak
    0.34
    🔃
    0.34
    POSITIVE LOGITS
    is
    0.45
     and
    0.44
     property
    0.42
    es
    0.41
    ()
    0.40
    ().
    0.40
     substring
    0.38
     financial
    0.38
    (),
    0.38
     predicate
    0.37
    Act Density 0.118%

    No Known Activations