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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (){
    -0.08
    мя
    -0.07
    promotion
    -0.06
    Если
    -0.06
    Environment
    -0.06
    =(-
    -0.06
     Harvest
    -0.06
     Rolled
    -0.06
     ler
    -0.06
    .should
    -0.06
    POSITIVE LOGITS
    .segment
    0.07
     προ
    0.06
     vzdělávání
    0.06
     PyObject
    0.06
    ashire
    0.06
    िसम
    0.06
     attacks
    0.06
    です
    0.06
    .CreateCommand
    0.06
     Plug
    0.06
    Act Density 0.024%

    No Known Activations