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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ✴
    -0.08
     TAX
    -0.08
    带队
    -0.07
     STM
    -0.07
     Pony
    -0.07
     באותה
    -0.07
    ))"↵
    -0.07
    ➔
    -0.07
     באותו
    -0.07
    鲅
    -0.07
    POSITIVE LOGITS
    (↵
    0.07
    __(
    0.07
    .environ
    0.07
    .net
    0.07
     Bình
    0.06
    ケー�
    0.06
     leader
    0.06
    輕
    0.06
    =r
    0.06
    .region
    0.06
    Act Density 0.019%

    No Known Activations