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

    Neuronpedia

    INDEX
    Explanations

    response.content parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFile
    0.38
    Entry
    0.37
    write
    0.37
     Lust
    0.36
    writeHead
    0.36
    Segment
    0.35
    writ
    0.35
    婚礼
    0.35
    Contracts
    0.35
    Deposit
    0.35
    POSITIVE LOGITS
     prefecture
    0.60
    prefetch
    0.59
     Pref
    0.56
     prefect
    0.55
     pref
    0.51
     annotate
    0.46
     order
    0.45
     values
    0.45
     lamang
    0.45
     USING
    0.44
    Act Density 0.006%

    No Known Activations