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

    Neuronpedia

    INDEX
    Explanations

    references to tables and their arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    tables and desks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.41
     informée
    -0.36
     Paglinawan
    -0.35
    WithMany
    -0.35
    Personendaten
    -0.35
     saben
    -0.34
    writeField
    -0.34
    jublj
    -0.34
    ParallelGroup
    -0.34
     jepang
    -0.34
    POSITIVE LOGITS
     table
    1.05
     tables
    1.04
     desks
    0.98
     desk
    0.92
     Table
    0.91
     Tables
    0.90
    Tables
    0.88
     Desk
    0.87
     tavolo
    0.85
    desk
    0.82
    Act Density 0.061%

    No Known Activations