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

    Neuronpedia

    INDEX
    Explanations

    dass; der; die; das

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ureux
    1.30
     пункта
    1.30
     kira
    1.29
     biasing
    1.29
     bekam
    1.28
     constitué
    1.27
     personnage
    1.23
     mezzi
    1.22
     kerajaan
    1.22
     pengertian
    1.22
    POSITIVE LOGITS
    ن
    1.77
    ل
    1.73
    ू
    1.72
    र
    1.67
    ল
    1.60
    ли
    1.58
    م
    1.58
    ار
    1.53
    ب
    1.51
    r
    1.50
    Act Density 0.052%

    No Known Activations