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

    Neuronpedia

    INDEX
    Explanations

    building and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tive
    1.32
    tiff
    1.22
     bushes
    1.21
    Ꭽ
    1.18
     akibat
    1.17
     PKK
    1.17
     markings
    1.16
    EIS
    1.15
    ༸
    1.14
     allegiance
    1.14
    POSITIVE LOGITS
    li
    0.93
    so
    0.89
    ~/
    0.82
     योग्य
    0.81
    ご了承ください
    0.81
    ု
    0.80
    stable
    0.80
    liu
    0.80
    なります
    0.80
    َا
    0.80
    Act Density 0.000%

    No Known Activations