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

    Neuronpedia

    INDEX
    Explanations

    Plural markers and parenthesized expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anso
    0.80
     চার
    0.79
     quotidienne
    0.77
     widescreen
    0.75
    anco
    0.74
    indak
    0.74
    ска
    0.74
     ―
    0.73
     mitral
    0.73
    ാൽ
    0.73
    POSITIVE LOGITS
    들
    1.18
    (
    0.97
    们
    0.96
    es
    0.89
    গুলি
    0.88
    들을
    0.87
    들의
    0.85
    들에
    0.85
    們
    0.84
    ें
    0.83
    Act Density 0.063%

    No Known Activations