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

    Neuronpedia

    INDEX
    Explanations

    understanding if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    node
    0.22
     এছাড়া
    0.20
    color
    0.19
    line
    0.19
    cfg
    0.18
    time
    0.18
    times
    0.18
    X
    0.18
    ground
    0.17
    start
    0.17
    POSITIVE LOGITS
     tentang
    0.28
     bahwa
    0.26
     banget
    0.26
     wholeheartedly
    0.24
     rằng
    0.24
     kwamba
    0.22
     instinctively
    0.21
     about
    0.21
     bahawa
    0.21
     Tentang
    0.21
    Act Density 0.908%

    No Known Activations