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

    Neuronpedia

    INDEX
    Explanations

    specific conditions or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Broken
    0.54
    Predicate
    0.53
    Determin
    0.49
    Acetic
    0.47
    broken
    0.47
    Controlled
    0.47
    Hoe
    0.46
    dataPro
    0.46
    Changed
    0.45
     decrees
    0.45
    POSITIVE LOGITS
     hizo
    0.57
    ak
    0.50
     tor
    0.47
     håller
    0.47
     rätt
    0.46
     l
    0.46
     يح
    0.46
     llevó
    0.45
    塢
    0.45
     sans
    0.45
    Act Density 0.002%

    No Known Activations