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

    Neuronpedia

    INDEX
    Explanations

    explanatory phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bot
    0.42
     mailed
    0.40
    ocracy
    0.39
    Dias
    0.38
     talk
    0.38
    represent
    0.37
    Views
    0.37
     pie
    0.37
    лат
    0.36
    겼
    0.36
    POSITIVE LOGITS
    hov
    0.40
    朲
    0.40
     käyttö
    0.39
     প্রয়োজন
    0.38
    0.37
     WHIT
    0.36
     防止
    0.36
     реєстра
    0.36
    看见
    0.35
     necesitas
    0.35
    Act Density 0.000%

    No Known Activations