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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excess
    0.70
     vacuum
    0.68
     nothing
    0.63
     limited
    0.62
     coils
    0.62
     Vacuum
    0.60
     earlier
    0.60
     pressure
    0.59
     severely
    0.59
     stunted
    0.59
    POSITIVE LOGITS
    ，《
    1.14
    ,//
    1.13
    ,【
    1.11
    ,/*
    1.09
    ));
    1.08
    \},
    1.07
    ,...
    1.06
    ،
    1.04
    ፣
    1.04
    ,[
    1.03
    Act Density 0.094%

    No Known Activations