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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unsere
    -0.07
     jamais
    -0.07
     пу
    -0.07
    ergy
    -0.06
     fierce
    -0.06
     omn
    -0.06
     回
    -0.06
    istance
    -0.06
     Davidson
    -0.06
     scept
    -0.06
    POSITIVE LOGITS
     DIY
    0.07
     所
    0.06
     AMC
    0.06
    .HttpServletResponse
    0.06
    开展
    0.06
    Conv
    0.06
     grounding
    0.06
     Abb
    0.06
     hơi
    0.06
    dg
    0.06
    Act Density 0.023%

    No Known Activations