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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &___
    -0.73
     متعلقه
    -0.68
    المناصب
    -0.66
    modelBuilder
    -0.65
    setColumns
    -0.64
     Económica
    -0.62
    TypedDataSet
    -0.62
     estimés
    -0.61
    MockMvc
    -0.61
     ostavi
    -0.60
    POSITIVE LOGITS
     dalamnya
    0.48
    رافی
    0.45
    unanje
    0.45
     famí
    0.45
    ResumeLayout
    0.44
    hoeddwyd
    0.43
     dis
    0.41
     des
    0.40
    прав
    0.40
     relaxed
    0.40
    Act Density 0.003%

    No Known Activations