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

    Neuronpedia

    INDEX
    Explanations

    using, seeking, avoiding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.78
     offerings
    0.73
    у
    0.71
    op
    0.70
    가가
    0.70
     workings
    0.70
    ch
    0.68
     وعلى
    0.67
    ia
    0.66
     Picks
    0.66
    POSITIVE LOGITS
    ل
    0.94
    器
    0.85
    कार्य
    0.82
    нде
    0.80
    elekt
    0.80
    нг
    0.77
    க
    0.77
    には
    0.77
    と思います
    0.76
    siniz
    0.75
    Act Density 0.448%

    No Known Activations