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

    Neuronpedia

    INDEX
    Explanations

    Other language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Williamsburg
    0.41
    orgt
    0.40
     Rachael
    0.40
     بہترین
    0.38
     multig
    0.38
     tubs
    0.38
     ব্র্যান্ড
    0.38
     Huntingdon
    0.38
     multimillion
    0.38
     Bedford
    0.37
    POSITIVE LOGITS
    OTROS
    0.50
     explore
    0.46
    Autres
    0.45
     другими
    0.45
    अनु
    0.44
    ponde
    0.44
     পড়িয়া
    0.44
    Siehe
    0.44
    ሣ
    0.43
    หรับ
    0.42
    Act Density 0.001%

    No Known Activations