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

    Neuronpedia

    INDEX
    Explanations

    want followed by a request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dale
    0.48
     вя
    0.46
    oleon
    0.45
    的网络
    0.44
    <unused41>
    0.43
     ³
    0.43
    ².
    0.42
     obligado
    0.42
    最优
    0.42
     нео
    0.40
    POSITIVE LOGITS
    実施
    0.50
    ಬ
    0.49
    को
    0.47
    ک
    0.47
     emphas
    0.46
    ປະ
    0.45
     リア
    0.45
     प्रशास
    0.45
    ुल
    0.44
    ああ
    0.44
    Act Density 0.001%

    No Known Activations