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

    Neuronpedia

    INDEX
    Explanations

    markdown formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palais
    0.45
     peroneal
    0.42
     treasurer
    0.41
     taped
    0.41
     caricature
    0.40
     RECEIPTS
    0.39
    ೆಂಟ್
    0.39
     vasocon
    0.38
    ENER
    0.38
    肚子
    0.37
    POSITIVE LOGITS
     Markdown
    2.31
    Markdown
    2.20
     markdown
    2.19
    markdown
    2.05
    md
    1.00
     markup
    0.97
     md
    0.95
     YAML
    0.93
     MD
    0.89
    MD
    0.89
    Act Density 0.033%

    No Known Activations