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

    Neuronpedia

    INDEX
    Explanations

    previously formerly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aka
    0.47
    ствовали
    0.47
    к
    0.46
     તમને
    0.43
    ari
    0.42
    कोई
    0.41
    ᑯ
    0.41
    cja
    0.41
     منك
    0.41
    šana
    0.40
    POSITIVE LOGITS
     previously
    0.59
     formerly
    0.54
     heretofore
    0.54
     hitherto
    0.52
     précédemment
    0.52
     tidligere
    0.50
     Previously
    0.48
     আগেও
    0.48
     Formerly
    0.48
     bislang
    0.47
    Act Density 0.001%

    No Known Activations