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

    Neuronpedia

    INDEX
    Explanations

    song chorus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鱔
    0.50
     хвати
    0.49
     enthalpies
    0.47
     ሽፋ
    0.47
     وګ
    0.47
     تھیں۔
    0.46
     allotments
    0.46
    RIBUT
    0.45
     ജൂ
    0.45
    ьера
    0.45
    POSITIVE LOGITS
     s
    0.50
    DS
    0.47
     as
    0.47
     stay
    0.47
     Hospital
    0.47
     relative
    0.46
    \
    0.45
     gada
    0.44
    金
    0.44
     game
    0.44
    Act Density 0.001%

    No Known Activations