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

    Neuronpedia

    INDEX
    Explanations

    for all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occasioned
    0.43
     Considerations
    0.39
     consideration
    0.38
    ="@+
    0.38
    Anything
    0.38
     Consideration
    0.38
     consideradas
    0.38
    ﹋
    0.38
     Anything
    0.37
    σίας
    0.37
    POSITIVE LOGITS
     sufficiently
    0.53
     some
    0.44
     ∀
    0.44
     suitably
    0.43
     fixed
    0.42
    jada
    0.42
     некоторые
    0.40
     qualche
    0.39
    forall
    0.39
    0.39
    Act Density 0.012%

    No Known Activations