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

    Neuronpedia

    INDEX
    Explanations

    Van Pallandt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    0.45
    ۢ
    0.42
    뚫
    0.37
     ので
    0.37
    ಬ್ಬಿಣ
    0.37
    અ
    0.37
    ⋅
    0.37
     hammering
    0.36
    凄い
    0.36
    ๎
    0.35
    POSITIVE LOGITS
     oración
    0.41
    obra
    0.39
    </u>
    0.38
     Biosciences
    0.38
     sina
    0.37
     הד
    0.36
     miglia
    0.36
     מספר
    0.36
     citt
    0.35
    žen
    0.35
    Act Density 0.036%

    No Known Activations