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

    Neuronpedia

    INDEX
    Explanations

    biases & biology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ver
    0.67
     Er
    0.61
    يرا
    0.57
     died
    0.57
     calves
    0.56
     Gloves
    0.55
    aghe
    0.55
    vere
    0.55
    Grunge
    0.54
    fers
    0.54
    POSITIVE LOGITS
    ান্তর
    0.67
    ليا
    0.64
     motiva
    0.64
     একদিকে
    0.63
    棻
    0.63
     ذریع
    0.62
     motivo
    0.62
     situado
    0.62
     Effekt
    0.61
     чуть
    0.60
    Act Density 0.169%

    No Known Activations