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

    Neuronpedia

    INDEX
    Explanations

    finding solutions to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    も
    0.64
    ને
    0.61
    まあ
    0.59
    搡
    0.59
     reaping
    0.57
    ndo
    0.56
    िता
    0.56
     Kardash
    0.56
    惴
    0.56
     बरत
    0.55
    POSITIVE LOGITS
    solution
    1.15
     solution
    0.97
     oplossing
    0.95
     সমাধান
    0.94
    solutions
    0.91
     해결
    0.91
     SOLUTION
    0.91
     rozwią
    0.88
     Lösung
    0.87
     solutions
    0.87
    Act Density 0.095%

    No Known Activations