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

    Neuronpedia

    INDEX
    Explanations

    Python strategy, lifetime warranty, broken screen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     troops
    0.57
     gates
    0.51
     Senators
    0.47
     soldier
    0.47
     meager
    0.46
     völlig
    0.46
     warrior
    0.46
     senators
    0.46
     വരെ
    0.45
     silencing
    0.45
    POSITIVE LOGITS
    (()
    0.53
     கற்ற
    0.49
    𝚔
    0.47
    что
    0.47
    いただきました
    0.46
    வதற்கான
    0.46
     পাচ
    0.46
    ohyd
    0.45
    चित्र
    0.45
    cosity
    0.44
    Act Density 0.000%

    No Known Activations