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

    Neuronpedia

    INDEX
    Explanations

    current feelings and sensations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ace
    0.28
     cereals
    0.28
    AI
    0.27
    H
    0.27
    b
    0.27
    display
    0.27
    gr
    0.27
    ui
    0.27
    ba
    0.27
    len
    0.26
    POSITIVE LOGITS
    我现在
    0.39
     selama
    0.37
    我很
    0.36
    ตอนนี้
    0.35
     ngayon
    0.34
     myself
    0.34
     sekarang
    0.34
     lately
    0.33
     sinds
    0.33
     ரொம்ப
    0.32
    Act Density 0.119%

    No Known Activations