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

    Neuronpedia

    INDEX
    Explanations

    traditional/classic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Australia
    0.45
     Australian
    0.44
     australia
    0.42
     Australien
    0.41
     Australians
    0.41
     ऑस्ट्रेलियाई
    0.41
     austral
    0.41
     Austr
    0.40
    澳大利亚
    0.39
     kangaroos
    0.39
    POSITIVE LOGITS
    Б
    0.42
    She
    0.38
    చ
    0.36
    Group
    0.36
    мам
    0.35
    感染
    0.35
    творення
    0.35
    Could
    0.35
    AndTime
    0.35
    Н
    0.35
    Act Density 0.000%

    No Known Activations