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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting in structured data or programming contexts

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

    prefix with newline characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.55
    sizeCache
    -0.51
     surla
    -0.49
     дописавши
    -0.49
     BrowserModule
    -0.49
    клопе
    -0.49
    expandindo
    -0.48
    kloped
    -0.47
     getRule
    -0.45
    ↹
    -0.45
    POSITIVE LOGITS
    RIEL
    0.34
    writerow
    0.34
    äsident
    0.33
    mbor
    0.33
    kkue
    0.33
    Datuak
    0.32
    protoc
    0.32
    efeller
    0.32
    träger
    0.32
    änning
    0.31
    Act Density 0.017%

    No Known Activations