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

    Neuronpedia

    INDEX
    Explanations

    elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Condom
    -0.09
    _TOO
    -0.08
    zugehen
    -0.08
     Expense
    -0.08
    unkt
    -0.08
     ವೇಳ
    -0.08
     derni
    -0.08
     دری
    -0.07
     Intensive
    -0.07
     सम्मेलन
    -0.07
    POSITIVE LOGITS
     elements
    0.09
     aspects
    0.09
     yếu
    0.09
    因素
    0.08
    融合
    0.08
    融
    0.08
     typical
    0.08
    .Feature
    0.08
    Elements
    0.07
     blended
    0.07
    Act Density 0.010%

    No Known Activations