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

    Neuronpedia

    INDEX
    Explanations

    question starters (who, how)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heuristics
    0.52
     polynomial
    0.49
     determining
    0.49
     amyloid
    0.48
    determining
    0.48
     coefficients
    0.47
     heuristic
    0.47
     uncertainty
    0.46
     nutrient
    0.46
     instability
    0.46
    POSITIVE LOGITS
    ok
    0.69
    you
    0.62
    who
    0.61
    could
    0.58
    Ok
    0.57
    Alright
    0.55
     اوكي
    0.55
    lol
    0.55
    Who
    0.54
    YOU
    0.54
    Act Density 0.001%

    No Known Activations