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

    Neuronpedia

    INDEX
    Explanations

    css layout properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Viruses
    0.83
     Speicher
    0.80
     Virus
    0.79
     Electrochemical
    0.77
     frequencies
    0.72
     Bacteria
    0.72
     EEG
    0.72
     Ammonia
    0.71
     Saving
    0.70
     poisons
    0.69
    POSITIVE LOGITS
    padding
    1.76
     padding
    1.65
    margin
    1.61
    border
    1.45
    Padding
    1.42
     Padding
    1.37
     margin
    1.31
    Margin
    1.30
     border
    1.28
    PADDING
    1.26
    Act Density 0.586%

    No Known Activations