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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squads
    -0.08
     minted
    -0.08
     viên
    -0.08
     îi
    -0.08
     mbi
    -0.08
     mined
    -0.08
     Entire
    -0.08
     searchable
    -0.08
     لق
    -0.07
     Learned
    -0.07
    POSITIVE LOGITS
     cables
    0.18
     подключения
    0.18
     подключ
    0.17
    连接
    0.17
     wiring
    0.17
     connections
    0.16
     cable
    0.16
     connectors
    0.15
     wired
    0.15
     kabel
    0.15
    Act Density 0.093%

    No Known Activations