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

    Neuronpedia

    INDEX
    Explanations

    <-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    that
    -0.08
    -support
    -0.07
     受
    -0.07
    YG
    -0.07
     Stretch
    -0.07
     �
    -0.06
    Standard
    -0.06
    Level
    -0.06
     party
    -0.06
     Occupation
    -0.06
    POSITIVE LOGITS
     náklad
    0.07
    Contr
    0.07
     деревян
    0.07
    تمبر
    0.07
     informs
    0.06
     advice
    0.06
     <-
    0.06
    REF
    0.06
     intimately
    0.06
    諸
    0.06
    Act Density 0.003%

    No Known Activations