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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worse
    -0.07
     Qui
    -0.07
     Apparel
    -0.06
    eper
    -0.06
    UDO
    -0.06
     лік
    -0.06
    ROID
    -0.06
    กว
    -0.06
    ाश
    -0.06
    ego
    -0.06
    POSITIVE LOGITS
     만족
    0.07
     mailed
    0.07
     infant
    0.07
    符合
    0.07
     Option
    0.07
     educated
    0.06
     Matth
    0.06
     fm
    0.06
    =train
    0.06
     shortcuts
    0.06
    Act Density 0.024%

    No Known Activations