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

    Neuronpedia

    INDEX
    Explanations

    financial charts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cor
    -0.06
     territor
    -0.06
    technical
    -0.06
    etus
    -0.06
     uf
    -0.06
    vak
    -0.06
     ideology
    -0.06
     Тер
    -0.06
    ạnh
    -0.06
     де
    -0.06
    POSITIVE LOGITS
     пример
    0.06
    άρχ
    0.06
     Installation
    0.06
    во
    0.06
    ψει
    0.06
     frankly
    0.06
    μι
    0.06
    гляд
    0.06
    -release
    0.05
     appoint
    0.05
    Act Density 0.008%

    No Known Activations