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

    Neuronpedia

    INDEX
    Explanations

    defining or suggesting qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puedes
    0.49
     Puedes
    0.48
    RU
    0.47
    َّا
    0.46
    BusinessType
    0.45
     ผู้
    0.45
     アイアン
    0.44
     freaking
    0.43
     Segurança
    0.43
     влияет
    0.43
    POSITIVE LOGITS
    acted
    0.48
    变革
    0.45
    itect
    0.44
    rolled
    0.44
    ritic
    0.44
    cieron
    0.44
    istors
    0.43
    stantial
    0.43
    ended
    0.43
     donné
    0.43
    Act Density 0.016%

    No Known Activations