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

    Neuronpedia

    INDEX
    Explanations

    about yourself or subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itetty
    0.52
     বড়
    0.44
     ресурсов
    0.44
    Imports
    0.43
    ين
    0.42
    旗
    0.42
    harga
    0.42
    重ね
    0.42
    눔
    0.40
     kasut
    0.40
    POSITIVE LOGITS
     Lastly
    0.55
     अकॉर्डिंग
    0.48
    umbing
    0.47
    ointing
    0.45
     novella
    0.45
     God
    0.44
     Thereafter
    0.43
    निश्
    0.42
    ूँगा
    0.42
     Detective
    0.42
    Act Density 0.003%

    No Known Activations