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

    Neuronpedia

    INDEX
    Explanations

    functionality, functional safety, function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Denn
    0.96
    den
    0.91
     dinast
    0.88
    近平
    0.86
    డి
    0.86
     brunt
    0.84
     হাসান
    0.82
     inquirer
    0.82
     ダイヤモンド
    0.81
     airborne
    0.80
    POSITIVE LOGITS
    ality
    1.16
    LevelLinking
    1.14
     myFunction
    1.09
    Lifetime
    0.98
    ु
    0.94
    ents
    0.93
    廁
    0.93
     PURPOSE
    0.91
     அழை
    0.91
    alities
    0.90
    Act Density 0.214%

    No Known Activations