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

    Neuronpedia

    INDEX
    Explanations

    descriptions following pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     හෝ
    0.42
     或者
    0.41
     किंवा
    0.40
     veya
    0.40
    或者是
    0.39
     หรือ
    0.39
     oppure
    0.38
    或者
    0.38
    หรือ
    0.38
     или
    0.37
    POSITIVE LOGITS
     “[
    0.42
     unmistak
    0.38
     unmistakable
    0.38
     unambiguously
    0.37
     plaintiffs
    0.36
     "[
    0.36
     unmist
    0.35
     “(
    0.35
     “…
    0.35
     forty
    0.34
    Act Density 0.003%

    No Known Activations