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

    Neuronpedia

    INDEX
    Explanations

    code structure or data descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lieberman
    0.47
     assayed
    0.47
     diminution
    0.46
     declined
    0.45
     Canoe
    0.44
     IEnumerable
    0.43
     interpolated
    0.43
     спорттук
    0.42
     tantalum
    0.42
     rallied
    0.42
    POSITIVE LOGITS
    els
    0.46
    re
    0.46
    thread
    0.46
    cl
    0.46
    tech
    0.44
    cont
    0.43
    time
    0.43
    root
    0.43
    ți
    0.43
    humidity
    0.43
    Act Density 0.001%

    No Known Activations