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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical or top-down concepts

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

    down or bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uș
    -0.33
     myself
    -0.33
    chläge
    -0.32
     yourself
    -0.30
    ạy
    -0.29
     Himself
    -0.29
     ditutup
    -0.29
     sensaciones
    -0.29
     diras
    -0.29
     rằng
    -0.28
    POSITIVE LOGITS
     pstmt
    0.86
     Hotspur
    0.84
    Neymar
    0.79
    celotti
    0.69
     Neymar
    0.66
     صوتيه
    0.66
    volley
    0.65
     SqlParameter
    0.63
     Zidane
    0.61
    ximately
    0.59
    Act Density 0.001%

    No Known Activations