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
    ]]);↵
    -0.07
     consumption
    -0.07
     Dent
    -0.07
    _teacher
    -0.07
    .dx
    -0.06
     theatrical
    -0.06
     daughter
    -0.06
    Requirements
    -0.06
     overweight
    -0.06
    .addProperty
    -0.06
    POSITIVE LOGITS
     yö
    0.07
     tehdy
    0.07
    ัพท
    0.07
     hồi
    0.06
    clas
    0.06
    old
    0.06
     gọn
    0.06
    901
    0.06
     플레이
    0.06
    ,start
    0.06
    Act Density 0.061%

    No Known Activations