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

    Neuronpedia

    INDEX
    Explanations

    folklore, fold expressions, or formations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    эффици
    0.45
    on
    0.45
     ideale
    0.43
    MoodAnalyser
    0.41
    ছিলেন
    0.41
    uiden
    0.41
     pods
    0.41
    hips
    0.41
     ідэ
    0.40
     ஆசிரிய
    0.40
    POSITIVE LOGITS
    FOL
    0.73
    Fol
    0.69
     FOL
    0.68
     fol
    0.67
     Fol
    0.66
     折
    0.63
     Fold
    0.60
    Folder
    0.58
    折
    0.58
     Foli
    0.58
    Act Density 0.006%

    No Known Activations