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

    Neuronpedia

    INDEX
    Explanations

    being forced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.47
    ใน
    0.46
    നങ്ങൾ
    0.43
    薙
    0.43
    缁
    0.42
    ฉัน
    0.40
    incible
    0.40
    üle
    0.40
    ли
    0.40
    '?
    0.39
    POSITIVE LOGITS
     severely
    0.48
     প্রতার
    0.42
    小題
    0.42
    微分
    0.42
     doomed
    0.41
     fiancé
    0.41
     Wilfred
    0.41
     imperatives
    0.39
    線性
    0.39
     bystand
    0.39
    Act Density 0.001%

    No Known Activations