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

    Neuronpedia

    INDEX
    Explanations

    phrasing of prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uições
    0.68
     본격
    0.65
    க்கழக
    0.63
     diadakan
    0.63
    णिमा
    0.62
    첩
    0.62
     Mapa
    0.61
    ய்ப்ப
    0.61
    Gesellschaft
    0.60
    yendo
    0.59
    POSITIVE LOGITS
     wording
    3.33
     phrasing
    3.08
     phrases
    2.81
     words
    2.77
     worded
    2.54
     phrase
    2.42
     language
    2.35
    words
    2.23
     Words
    2.18
     Phrases
    2.12
    Act Density 3.217%

    No Known Activations