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

    Neuronpedia

    INDEX
    Explanations

    groups and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contains
    0.37
     Contains
    0.31
     enthält
    0.30
     appears
    0.30
    contains
    0.30
     yellowish
    0.30
     বলিল
    0.29
    螢
    0.29
    banana
    0.29
     whereupon
    0.28
    POSITIVE LOGITS
     должны
    0.38
     strive
    0.37
     berharap
    0.33
     trebui
    0.33
     bekerja
    0.33
     хотят
    0.33
     collectively
    0.32
     повинні
    0.32
     travailler
    0.32
     rejoice
    0.31
    Act Density 0.381%

    No Known Activations