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

    Neuronpedia

    INDEX
    Explanations

    meticulously planning before each study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verbindung
    0.59
     zum
    0.50
     godziny
    0.49
     sobri
    0.48
     Öff
    0.47
     refreshment
    0.47
     mieście
    0.46
     Epis
    0.46
     Stunden
    0.45
     XIII
    0.45
    POSITIVE LOGITS
    }$(
    0.48
    ⵔ
    0.47
    真
    0.46
    我
    0.46
    啊
    0.44
    也许
    0.44
    ش
    0.44
    何か
    0.42
    田
    0.42
     পাল্টা
    0.42
    Act Density 0.005%

    No Known Activations