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

    Neuronpedia

    INDEX
    Explanations

    providing indications and brief details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diferentes
    0.53
     különböző
    0.53
     verschiedenen
    0.52
     différentes
    0.51
     różnych
    0.50
     forskjellige
    0.49
     verschillende
    0.49
    Different
    0.47
     různých
    0.47
    Options
    0.47
    POSITIVE LOGITS
     italic
    0.76
     approximate
    0.71
     briefly
    0.67
     italics
    0.67
     parentheses
    0.65
    括号
    0.63
     noted
    0.63
    괄
    0.62
     brief
    0.61
     notation
    0.60
    Act Density 0.043%

    No Known Activations