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

    Neuronpedia

    INDEX
    Explanations

    placeholders or code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     குறிப்பிட்ட
    0.44
    _{-}^{
    0.42
    ylül
    0.41
     పేర్కొ
    0.41
     específ
    0.41
    Inser
    0.41
    Lymph
    0.40
     indicar
    0.40
    㐄
    0.40
    하였다
    0.40
    POSITIVE LOGITS
    ![
    0.43
     sulfides
    0.42
    )=[
    0.39
     organ
    0.39
     jungles
    0.38
     ople
    0.38
     ])
    0.37
    ierd
    0.37
     wilds
    0.37
     –
    0.37
    Act Density 0.016%

    No Known Activations