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

    Neuronpedia

    INDEX
    Explanations

    introducing detailed breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یداری
    0.44
     inventing
    0.43
    瞬间
    0.42
     utiles
    0.41
     questionnaires
    0.41
    ouses
    0.41
     motifs
    0.40
     instants
    0.40
    瞬間
    0.39
     instantaneously
    0.39
    POSITIVE LOGITS
     breakdown
    1.31
     rundown
    1.08
     Breakdown
    1.02
     overview
    1.01
     detailed
    0.97
     examination
    0.89
     look
    0.85
    overview
    0.82
     Detailed
    0.81
     breakdowns
    0.81
    Act Density 0.023%

    No Known Activations