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

    Neuronpedia

    INDEX
    Explanations

    common sentence structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opsi
    0.53
     webhook
    0.49
     கட்டமை
    0.49
     triage
    0.49
     showdown
    0.48
     stash
    0.48
     आइकन
    0.47
    配列
    0.46
     risque
    0.46
     récupérer
    0.46
    POSITIVE LOGITS
     tourists
    0.46
     Tourism
    0.46
     Pollution
    0.46
     Literature
    0.44
     tourism
    0.42
     pollution
    0.42
     However
    0.41
    しましたが
    0.41
     students
    0.40
     Paragraph
    0.40
    Act Density 0.429%

    No Known Activations