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

    Neuronpedia

    INDEX
    Explanations

    AvailabilityStatus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rame
    0.46
     elb
    0.45
     nomes
    0.44
     Linie
    0.43
     verir
    0.43
     stung
    0.43
     Kamane
    0.42
     liste
    0.42
     Braunschweig
    0.42
     adren
    0.42
    POSITIVE LOGITS
    by
    0.46
    xml
    0.46
    示
    0.46
     także
    0.44
     прад
    0.44
     crucially
    0.42
    确定
    0.42
    强调
    0.42
    APPLE
    0.42
    </h2>
    0.41
    Act Density 0.000%

    No Known Activations