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

    Neuronpedia

    INDEX
    Explanations

    diversity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mapping
    -0.07
    Nit
    -0.07
    ikh
    -0.07
     spur
    -0.07
    ',"
    -0.07
    ccd
    -0.07
    המשך
    -0.06
    规划建设
    -0.06
     sig
    -0.06
    筑
    -0.06
    POSITIVE LOGITS
     opportunity
    0.08
    _blank
    0.07
    玩家朋友
    0.07
     grabbed
    0.07
    的话题
    0.07
    /global
    0.06
     Friend
    0.06
    你的
    0.06
    (repository
    0.06
     LEVEL
    0.06
    Act Density 0.042%

    No Known Activations