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

    Neuronpedia

    INDEX
    Explanations

    familiar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abaixo
    -0.08
    Steven
    -0.07
    742
    -0.07
    .Nodes
    -0.07
    Paused
    -0.07
    Slot
    -0.07
    /string
    -0.06
     Secretary
    -0.06
    582
    -0.06
    =-
    -0.06
    POSITIVE LOGITS
     familiar
    0.09
     familiarity
    0.08
     DataAccess
    0.06
    幕
    0.06
    irs
    0.06
     distraction
    0.06
    ıldı
    0.06
     وظ
    0.06
    (reinterpret
    0.06
    .AutoSizeMode
    0.06
    Act Density 0.007%

    No Known Activations