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

    Neuronpedia

    INDEX
    Explanations

    narrative exploration and emotional impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    манов
    0.43
    Civil
    0.42
    healing
    0.42
    Healing
    0.42
    ແ
    0.42
     ड्राइव
    0.40
    Տ
    0.40
    Drive
    0.39
    Adult
    0.39
     Cren
    0.39
    POSITIVE LOGITS
     suspects
    0.53
     témoign
    0.46
     newValue
    0.46
     şi
    0.45
     dès
    0.45
     BIB
    0.44
     Describes
    0.44
     successivement
    0.44
     désormais
    0.44
     et
    0.43
    Act Density 0.001%

    No Known Activations