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

    Neuronpedia

    INDEX
    Explanations

    weight of 30 elephants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Australia
    0.50
     Australian
    0.50
     Aussie
    0.50
     Australien
    0.47
    澳洲
    0.46
     ऑस्ट्रेलिया
    0.46
     AUSTRAL
    0.45
     Australie
    0.45
     Australians
    0.44
     Austr
    0.44
    POSITIVE LOGITS
    Mamm
    0.37
    Thoreau
    0.36
    BTC
    0.35
    Scala
    0.34
     Jurassic
    0.33
    Twitter
    0.33
    Spanish
    0.33
    僕は
    0.33
    Siem
    0.33
    Finn
    0.33
    Act Density 0.000%

    No Known Activations