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

    Neuronpedia

    INDEX
    Explanations

    one of

    np_acts-logits-general · gemini-2.5-flash-lite

    my + affectionate terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aussie
    0.52
     ऑस्ट्रेलियाई
    0.52
     Australian
    0.49
    Australian
    0.48
     Australien
    0.47
     Auss
    0.45
     ऑस्ट्रेलिया
    0.45
    澳大利亚
    0.43
     Australie
    0.43
     AUSTRAL
    0.43
    POSITIVE LOGITS
    DISCUSSION
    0.41
     Discuss
    0.38
    anh
    0.38
     Discussion
    0.38
     List
    0.37
     discussion
    0.37
    discussion
    0.37
    ሐ
    0.37
    Dictionary
    0.36
    ПР
    0.36
    Act Density 0.000%

    No Known Activations