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

    Neuronpedia

    INDEX
    Explanations

    explaining ChatGPT to an audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Municipio
    0.47
     पांडे
    0.46
     Лука
    0.46
     Sonntag
    0.46
     रेफर
    0.46
    них
    0.45
     Bảo
    0.45
     diá
    0.45
     Bonifacio
    0.45
     Леон
    0.44
    POSITIVE LOGITS
    er
    0.55
    一段
    0.51
     headway
    0.48
    发放
    0.45
    ur
    0.44
    rook
    0.42
    Changed
    0.42
    üse
    0.42
     άλ
    0.42
    ዒ
    0.41
    Act Density 0.001%

    No Known Activations