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

    Neuronpedia

    INDEX
    Explanations

    introducing lists or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    您可以
    0.50
    你可以
    0.49
    രാണ്
    0.48
     మీరు
    0.47
    ής
    0.45
    我们将
    0.44
     আপনারা
    0.43
    πάρχ
    0.42
    伱
    0.42
     siguiente
    0.42
    POSITIVE LOGITS
    fections
    0.38
    }
    0.38
     AII
    0.37
     심
    0.36
     subjug
    0.36
     мес
    0.35
     arv
    0.35
     sexu
    0.35
    crets
    0.34
     parti
    0.34
    Act Density 0.101%

    No Known Activations