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

    Neuronpedia

    INDEX
    Explanations

    terraform providers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modelu
    0.42
     Hoyt
    0.41
    müş
    0.40
     hewan
    0.40
    াঙ্গা
    0.40
    stätten
    0.40
     пап
    0.39
    owiada
    0.39
     پرس
    0.39
     Wojcie
    0.39
    POSITIVE LOGITS
     suggested
    0.63
    Suggested
    0.62
     Suggested
    0.60
     suger
    0.51
     recommended
    0.48
     sugg
    0.47
    Recommended
    0.46
     sugger
    0.46
     Recommended
    0.45
    建议
    0.42
    Act Density 0.001%

    No Known Activations