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

    Neuronpedia

    INDEX
    Explanations

    error handling and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complesso
    0.43
     striking
    0.42
     relates
    0.41
     series
    0.41
     twins
    0.41
     veya
    0.40
     ole
    0.40
     maintain
    0.39
     remain
    0.39
     follow
    0.38
    POSITIVE LOGITS
     changeset
    0.45
    ธุ
    0.44
    เปลี่ยนแปลง
    0.42
     mism
    0.40
     रेन
    0.39
     خس
    0.39
    rainte
    0.38
    ยายาม
    0.38
    பா
    0.38
    ällt
    0.38
    Act Density 0.033%

    No Known Activations