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

    Neuronpedia

    INDEX
    Explanations

    delve deeper into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addressed
    0.69
     addressing
    0.69
    تحان
    0.68
     acknowledge
    0.66
     tackle
    0.66
    谈
    0.65
    Retry
    0.65
     address
    0.64
    Addressing
    0.64
    wirken
    0.64
    POSITIVE LOGITS
     dives
    1.33
     digging
    1.22
     dug
    1.21
     digs
    1.17
     diving
    1.15
    深
    1.15
     dig
    1.14
     dive
    1.13
     deep
    1.10
     delves
    1.09
    Act Density 0.039%

    No Known Activations