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

    Neuronpedia

    INDEX
    Explanations

    information on problems and solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     materiality
    0.41
     च
    0.40
     प्रवाह
    0.40
    🧪
    0.40
     Webinar
    0.40
    畊
    0.39
     mú
    0.39
     Hospitality
    0.39
     webinar
    0.38
    Executive
    0.38
    POSITIVE LOGITS
     epidermal
    0.43
     creams
    0.42
    linear
    0.42
     swollen
    0.42
     swore
    0.41
     annoyed
    0.41
     cutaneous
    0.40
     inflamed
    0.40
    abulous
    0.40
     sixteenth
    0.39
    Act Density 0.003%

    No Known Activations