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

    Neuronpedia

    INDEX
    Explanations

    contain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     risky
    -0.07
    僕
    -0.06
     ump
    -0.06
    Budget
    -0.06
     IOC
    -0.06
     rise
    -0.06
     sage
    -0.06
     hızlı
    -0.06
     wichtig
    -0.06
     optimization
    -0.06
    POSITIVE LOGITS
     contain
    0.11
     contains
    0.11
     containing
    0.10
     contained
    0.10
     Contains
    0.09
    ان
    0.08
     possessing
    0.08
    تن
    0.08
    contains
    0.07
    aman
    0.07
    Act Density 0.042%

    No Known Activations