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

    Neuronpedia

    INDEX
    Explanations

    Remote Play and doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    norr
    0.40
    newData
    0.38
     interleaved
    0.37
     equity
    0.37
    putes
    0.36
     nam
    0.36
     kim
    0.36
    AntiForgeryToken
    0.36
    prises
    0.35
     수상
    0.35
    POSITIVE LOGITS
    镜
    0.41
     correlated
    0.39
     responding
    0.37
     Wolf
    0.36
     Dialer
    0.36
    ”(
    0.35
    เกี่ยวข้อง
    0.35
     Young
    0.35
    Wolf
    0.34
     दिलाने
    0.34
    Act Density 0.000%

    No Known Activations