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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haji
    0.58
    দায়িক
    0.55
    дія
    0.54
    Ｈ
    0.54
     Hack
    0.51
    AO
    0.51
    maximizing
    0.51
    畚
    0.51
     AO
    0.50
     Schwarzen
    0.50
    POSITIVE LOGITS
     된
    0.57
     религи
    0.57
     vacate
    0.57
     الات
    0.57
     populate
    0.56
     الاست
    0.55
    ∂</
    0.55
    vil
    0.55
     রাকাত
    0.55
     cantidad
    0.54
    Act Density 0.000%

    No Known Activations