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

    Neuronpedia

    INDEX
    Explanations

    references to user interface elements and their properties in code

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

    request user command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.72
     ujednoznacz
    -0.64
     صوتيه
    -0.59
     gynhyrchwyd
    -0.52
    úgó
    -0.52
    enumi
    -0.50
     Administrativna
    -0.49
    ExtendWith
    -0.49
    الحياه
    -0.48
     Fotografie
    -0.47
    POSITIVE LOGITS
    persky
    0.37
    WH
    0.33
     webdriver
    0.32
    gonic
    0.32
    SequentialGroup
    0.32
    YSTEM
    0.31
    cassert
    0.30
    reff
    0.29
    mbic
    0.29
    namics
    0.28
    Act Density 0.028%

    No Known Activations