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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic and Slavic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Richardson
    -0.07
    Mech
    -0.07
     shelters
    -0.07
    .ga
    -0.07
     Shi
    -0.07
    stinence
    -0.06
    cms
    -0.06
    userInfo
    -0.06
    步步
    -0.06
    觱
    -0.06
    POSITIVE LOGITS
     Goal
    0.07
     repeal
    0.07
    삣
    0.07
     Glacier
    0.07
    왠
    0.07
    ߟ
    0.07
     Delivery
    0.06
    펼
    0.06
    𝘔
    0.06
     الكلام
    0.06
    Act Density 0.046%

    No Known Activations