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

    Neuronpedia

    INDEX
    Explanations

    relative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anlam
    -0.07
    .Exchange
    -0.07
    ikes
    -0.07
    ろう
    -0.06
     price
    -0.06
     peach
    -0.06
     maiden
    -0.06
    ynch
    -0.06
     مشتر
    -0.06
     구조
    -0.06
    POSITIVE LOGITS
     boast
    0.07
    QUESTION
    0.07
     بح
    0.07
     MOS
    0.06
     sessionStorage
    0.06
     брон
    0.06
    _v
    0.06
     ανα
    0.06
    adress
    0.06
    Parent
    0.06
    Act Density 0.007%

    No Known Activations