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

    Neuronpedia

    INDEX
    Explanations

    programming-related functions and keywords

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

    `<start_of_turn> user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rubin
    -0.40
    Diweddarwch
    -0.39
    ghalaya
    -0.38
    RefNanny
    -0.37
     personali
    -0.36
     extended
    -0.36
    extAlignment
    -0.35
    äsent
    -0.35
     veto
    -0.35
    ContentValues
    -0.35
    POSITIVE LOGITS
    HandlerContext
    0.59
    netty
    0.49
    :✨
    0.47
     يتيمه
    0.46
    expandindo
    0.45
    kháu
    0.45
    جستارهای
    0.44
    fjspx
    0.44
    تقاوى
    0.43
    Jaunes
    0.43
    Act Density 0.002%

    No Known Activations