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

    Neuronpedia

    INDEX
    Explanations

    get back on track

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sometimes
    0.39
    க்கப்பட்ட
    0.38
     strawberries
    0.36
     trams
    0.35
     VIII
    0.35
    دين
    0.35
     Tram
    0.35
    ிறு
    0.35
    দৈ
    0.35
     ऊंचा
    0.34
    POSITIVE LOGITS
    ustellen
    0.40
    硒
    0.40
    ائِ
    0.40
    部分
    0.39
    isticated
    0.39
    ⤥
    0.38
    Centered
    0.38
    菏
    0.38
     छोड़
    0.38
    ijos
    0.38
    Act Density 0.000%

    No Known Activations