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

    Neuronpedia

    INDEX
    Explanations

    PDF files and downloads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    3.52
     употре
    3.25
    ত
    2.89
    tedir
    2.86
     대해
    2.72
     publicados
    2.65
    "\
    2.64
     изба
    2.62
    ುವ
    2.61
    கள்
    2.56
    POSITIVE LOGITS
    𝓊
    3.14
    ch
    2.97
    𝒔
    2.86
    м
    2.72
    𝖽
    2.65
    귿
    2.54
    𝓂
    2.53
    }|
    2.53
    ை
    2.51
     gson
    2.50
    Act Density 0.074%

    No Known Activations