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

    Neuronpedia

    INDEX
    Explanations

    social norms and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ce
    1.45
    sthe
    1.27
    َهُ
    1.25
    straße
    1.23
    近年来
    1.22
    gleichen
    1.21
    erver
    1.20
    𝗰
    1.20
    clud
    1.19
    र्तन
    1.16
    POSITIVE LOGITS
    א
    1.32
    έ
    1.27
    ט
    1.21
    ف
    1.17
     económicas
    1.13
     forskj
    1.12
     народу
    1.10
    ेटिव
    1.09
    Bep
    1.07
    所有
    1.04
    Act Density 0.003%

    No Known Activations