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

    Neuronpedia

    INDEX
    Explanations

    distance measurements in miles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жник
    0.55
    prés
    0.55
    option
    0.54
     practised
    0.52
    rejected
    0.52
     ebenfalls
    0.50
     tiež
    0.50
    ﺲ
    0.50
    ަ
    0.49
     przed
    0.49
    POSITIVE LOGITS
     여러분
    0.63
     Commanders
    0.58
     Translation
    0.58
    私たち
    0.57
     legenda
    0.54
     Entom
    0.54
    芎
    0.53
    我们
    0.53
     ফ্লাইট
    0.52
    ophiles
    0.52
    Act Density 0.001%

    No Known Activations